{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import arviz as az\n", "import numpy as np\n", "import pandas as pd\n", "import pymc as pm\n", "from matplotlib import pyplot as plt\n", "from patsy import dmatrix\n", "\n", "import causalpy as cp\n", "\n", "## Setting for Mac OS spawning multi-process defaults on M1 chip\n", "sampler_kwargs = {\n", " \"tune\": 2000,\n", " \"draws\": 2000,\n", " \"target_accept\": 0.95,\n", " \"mp_ctx\": \"spawn\",\n", " \"random_seed\": 1040,\n", "}" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## The Paradox of Propensity Scores in Bayesian Inference\n", "\n", "In causal inference the role of the propensity score is often seen to be central. For instance, [we've seen](https://causalpy.readthedocs.io/en/latest/notebooks/inv_prop_pymc.html) how the {term}`propensity score` can be used with the `cp.InversePropensityWeighting` class to correct for a species of selection bias by re-weighting our outcome variable and calculating a causal contrast on the re-weighted scale. Additionally we can use the propensity score to visualise and diagnose problems of overlap or covariate balancing across treatment and control groups. \n", "\n", "These properties give the propensity score a large role to play in _design based_ approaches to causal inference. The focus there is on assessing aspects of the treatment allocation to ensure we have identifiability assurances for estimands of interest. What then is their role in model-based or analysis focused Bayesian methods?\n", "\n", "When we use `cp.InversePropensityWeighting` to apply various re-weighting techniques we perform a two-step manoeuvre: 1. we estimate the propensity score and 2. apply the inverse-weighting of the score to transform our outcome variable and assess causal contrasts. But being good Bayesians, we might wonder why go to all this trouble? Can we not simply estimate a full-bayesian model of treatment and outcome simultaneously?\n", "\n", "In this notebook we'll show why we should be careful attempting to model the joint-distribution of the propensity score and the outcome variable, but still make good use of the propensity score. \n", "\n", "#### Brief Digression on the Mathematics\n", "\n", "Consider that we have the following three variables:\n", "\n", "$$ P(Y, T, X) $$ \n", "\n", "where $Y$ is our outcome variable, $T$ is our treatment variable, and $X$ stands in for all other control variables in scope. Now define the propensity score\n", "\n", "$$ e(X) = P(T | X)$$\n", "\n", "and our outcome model\n", "\n", "$$\\begin{align*}\n", "P(Y \\mid T, X) &= \\frac{P(Y, T, X)}{P(T, X)} \\cdot P(T, X) \\\\\n", "&= \\frac{P(Y \\mid T, X) \\cdot P(T \\mid X) \\cdot P(X)}{P(T \\mid X) \\cdot P(X)} \\cdot P(T, X) \\\\\n", "&= \\frac{P(Y \\mid T, X) \\cdot e(X) \\cdot P(X)}{e(X) \\cdot P(X)} \\cdot P(T, X)\n", "\\end{align*}\n", "$$\n", "\n", "but now it's clearer to see how the propensity score just cancels out. When we're already conditioning on $X, T$ the information in the propensity score is technically redundant in the Bayesian setting. Add the assumption of unconfoundedness or ignorability used in causal inference. We are arguing that there is no umeasured confounding so conditioning on $X, T$ should be sufficient to identify the causal contrast of interest. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Structure of the Presentation\n", "\n", "We will first consider a simple simulated data set where we know the true values of the data generating process and then we'll demonstrate how to fit the joint distribution of the propensity score and the outcome in a single joint distribution using `PyMC`. To contrast this we'll show how to fit a two-stage version of the same model. In both models we assume independent priors between the regression for the treatment and the regression for the outcome variable. Nevertheless, we will show that the joint model exhibits a bias due to feedback when there is non-measured confounding i.e. when there is misspecified outcome model. \n", "\n", "- Model Specification\n", " - `Specifying the Joint Model`\n", " - `Specifying the 2 Stage Model`\n", "- Application to Simulated Outcome\n", "- Application to Mosquito Net Data\n", "- Application to Lalonde Data\n", "- Application to NHEFS data.\n", "\n", "Note the presentation here owes a debt to the work of Fan Li in {cite:p}`liBayesianProp` and her presentation [here](https://youtu.be/_BjkF2nl7dg?si=Pmza3EoTpz-flT8m&t=26). Additionally we drew on the work and data of Andrew Heiss [here](https://www.andrewheiss.com/blog/2021/12/18/bayesian-propensity-scores-weights/) and Jordan Nafa and Andrew Heiss [here](https://www.andrewheiss.com/blog/2021/12/20/fully-bayesian-ate-iptw/). " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Generate Some Data" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
x1x2x3trtoutcome
00.570753-1.3729920.24782401.114661
10.0639730.9047280.32222212.952142
2-0.356653-0.188922-1.36904105.809954
3-1.372285-0.611158-1.75524205.509733
40.0299551.773686-0.45537116.058045
\n", "
" ], "text/plain": [ " x1 x2 x3 trt outcome\n", "0 0.570753 -1.372992 0.247824 0 1.114661\n", "1 0.063973 0.904728 0.322222 1 2.952142\n", "2 -0.356653 -0.188922 -1.369041 0 5.809954\n", "3 -1.372285 -0.611158 -1.755242 0 5.509733\n", "4 0.029955 1.773686 -0.455371 1 6.058045" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "N = 4000\n", "np.random.seed(1043)\n", "\n", "\n", "def inv_logit(z):\n", " \"\"\"Compute the inverse logit (sigmoid) of z.\"\"\"\n", " return 1 / (1 + np.exp(-z))\n", "\n", "\n", "df1 = pd.DataFrame(\n", " {\n", " \"x1\": np.random.normal(0, 1, N),\n", " \"x2\": np.random.normal(0, 1, N),\n", " \"x3\": np.random.normal(0, 1, N),\n", " }\n", ")\n", "\n", "TREATMENT_EFFECT = 2\n", "df1[\"trt\"] = np.random.binomial(1, inv_logit(df1[\"x1\"] + 6 * df1[\"x2\"] + 7 * df1[\"x3\"]))\n", "df1[\"outcome\"] = (\n", " 1\n", " + TREATMENT_EFFECT * df1[\"trt\"]\n", " + df1[\"x1\"]\n", " + 0.2 * df1[\"x2\"]\n", " + -3 * df1[\"x3\"]\n", " + np.random.normal(0, 1, N)\n", ")\n", "\n", "\n", "df1.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Specifying the Joint Model\n", "\n", "Now we define a model context that fits our data simultaneously for treatment and outcome. We allow that the propensity score estimated in the treatment model is used in a non-parametric spline to flexibly inform the outcome variable. Note that we will allow for a richer model specification of the treatment than we do for the outcome model. This is to try and push the models to use the propensity score information to adjust for unmeasured confounding in the outcome model. " ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "clusterobs (4000) x beta_trt (3)\n", "\n", "obs (4000) x beta_trt (3)\n", "\n", "\n", "clusterobs (4000) x betas (2)\n", "\n", "obs (4000) x betas (2)\n", "\n", "\n", "clusterobs (4000)\n", "\n", "obs (4000)\n", "\n", "\n", "clusterbetas_trt (3)\n", "\n", "betas_trt (3)\n", "\n", "\n", "clusterbetas (2)\n", "\n", "betas (2)\n", "\n", "\n", "\n", "X\n", "\n", "X\n", "~\n", "Data\n", "\n", "\n", "\n", "p\n", "\n", "p\n", "~\n", "Deterministic\n", "\n", "\n", "\n", "X->p\n", "\n", "\n", "\n", "\n", "\n", "X_outcome\n", "\n", "X_outcome\n", "~\n", "Data\n", "\n", "\n", "\n", "like\n", "\n", "like\n", "~\n", "Normal\n", "\n", "\n", "\n", "X_outcome->like\n", "\n", "\n", "\n", "\n", "\n", "Y\n", "\n", "Y\n", "~\n", "Data\n", "\n", "\n", "\n", "t_pred\n", "\n", "t_pred\n", "~\n", "Bernoulli\n", "\n", "\n", "\n", "T\n", "\n", "T\n", "~\n", "Data\n", "\n", "\n", "\n", "t_pred->T\n", "\n", "\n", "\n", "\n", "\n", "like->Y\n", "\n", "\n", "\n", "\n", "\n", "p->t_pred\n", "\n", "\n", "\n", "\n", "\n", "p->like\n", "\n", "\n", "\n", "\n", "\n", "beta_trt_std\n", "\n", "beta_trt_std\n", "~\n", "Normal\n", "\n", "\n", "\n", "beta_trt_\n", "\n", "beta_trt_\n", "~\n", "Deterministic\n", "\n", "\n", "\n", "beta_trt_std->beta_trt_\n", "\n", "\n", "\n", "\n", "\n", "beta_trt_->p\n", "\n", "\n", "\n", "\n", "\n", "beta_\n", "\n", "beta_\n", "~\n", "Deterministic\n", "\n", "\n", "\n", "beta_->like\n", "\n", "\n", "\n", "\n", "\n", "beta_std\n", "\n", "beta_std\n", "~\n", "Normal\n", "\n", "\n", "\n", "beta_std->beta_\n", "\n", "\n", "\n", "\n", "\n", "sigma\n", "\n", "sigma\n", "~\n", "HalfNormal\n", "\n", "\n", "\n", "sigma->like\n", "\n", "\n", "\n", "\n", "\n", "alpha_trt\n", "\n", "alpha_trt\n", "~\n", "Normal\n", "\n", "\n", "\n", "alpha_trt->p\n", "\n", "\n", "\n", "\n", "\n", "beta_ps\n", "\n", "beta_ps\n", "~\n", "Normal\n", "\n", "\n", "\n", "beta_ps->like\n", "\n", "\n", "\n", "\n", "\n", "alpha_outcome\n", "\n", "alpha_outcome\n", "~\n", "Normal\n", "\n", "\n", "\n", "alpha_outcome->like\n", "\n", "\n", "\n", "\n", "\n" ], "text/plain": [ "" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "coords = {\n", " \"betas\": [\"trt\", \"x1\"],\n", " \"betas_trt\": [\"x1\", \"x2\", \"x3\"],\n", " \"obs\": range(df1.shape[0]),\n", "}\n", "\n", "N = df1.shape[0]\n", "X_trt = df1[[\"x1\", \"x2\", \"x3\"]].values\n", "X_outcome = df1[[\"trt\", \"x1\"]].values\n", "T_data = df1[\"trt\"].values\n", "Y_data = df1[\"outcome\"].values\n", "\n", "\n", "def make_joint_model(\n", " X_trt,\n", " X_outcome,\n", " T_data,\n", " Y_data,\n", " coords,\n", " priors={\n", " \"beta_\": [0, 1],\n", " \"beta_trt\": [0, 1],\n", " \"alpha_trt\": [0, 1],\n", " \"alpha_outcome\": [0, 1],\n", " \"sigma\": 1,\n", " \"beta_ps\": [0, 1],\n", " },\n", " noncentred=True,\n", " normal_outcome=True,\n", "):\n", " with pm.Model(coords=coords) as model:\n", " X_data_trt = pm.Data(\"X\", X_trt, dims=(\"obs\", \"beta_trt\"))\n", " X_data_outcome = pm.Data(\"X_outcome\", X_outcome, dims=(\"obs\", \"betas\"))\n", " T_data_ = pm.Data(\"T\", T_data, dims=\"obs\")\n", " Y_data_ = pm.Data(\"Y\", Y_data, dims=\"obs\")\n", "\n", " if noncentred:\n", " mu_beta_trt, sigma_beta_trt = priors[\"beta_trt\"]\n", " beta_trt_std = pm.Normal(\"beta_trt_std\", 0, 1, dims=\"betas_trt\")\n", " beta_trt = pm.Deterministic(\n", " \"beta_trt_\",\n", " mu_beta_trt + sigma_beta_trt * beta_trt_std,\n", " dims=\"betas_trt\",\n", " )\n", "\n", " mu_beta, sigma_beta = priors[\"beta_\"]\n", " beta_std = pm.Normal(\"beta_std\", 0, 1, dims=\"betas\")\n", " beta = pm.Deterministic(\n", " \"beta_\", mu_beta + sigma_beta * beta_std, dims=\"betas\"\n", " )\n", " else:\n", " beta_trt = pm.Normal(\n", " \"beta_trt_\",\n", " priors[\"beta_trt\"][0],\n", " priors[\"beta_trt\"][1],\n", " dims=\"betas_trt\",\n", " )\n", "\n", " beta = pm.Normal(\n", " \"beta_\", priors[\"beta_\"][0], priors[\"beta_\"][1], dims=\"betas\"\n", " )\n", "\n", " beta_ps = pm.Normal(\"beta_ps\", priors[\"beta_ps\"][0], priors[\"beta_ps\"][1])\n", "\n", " alpha_trt = pm.Normal(\n", " \"alpha_trt\", priors[\"alpha_trt\"][0], priors[\"alpha_trt\"][1]\n", " )\n", " mu_trt = alpha_trt + pm.math.dot(X_data_trt, beta_trt)\n", " p = pm.Deterministic(\"p\", pm.math.invlogit(mu_trt), dims=\"obs\")\n", "\n", " pm.Bernoulli(\"t_pred\", p=p, observed=T_data_, dims=\"obs\")\n", "\n", " alpha_outcome = pm.Normal(\n", " \"alpha_outcome\", priors[\"alpha_outcome\"][0], priors[\"alpha_outcome\"][1]\n", " )\n", " mu_outcome = alpha_outcome + pm.math.dot(X_data_outcome, beta) + beta_ps * p\n", " sigma = pm.HalfNormal(\"sigma\", priors[\"sigma\"])\n", "\n", " if normal_outcome:\n", " _ = pm.Normal(\"like\", mu_outcome, sigma, observed=Y_data_, dims=\"obs\")\n", " else:\n", " nu = pm.Exponential(\"nu\", lam=1 / 10)\n", " _ = pm.StudentT(\n", " \"like\", nu=nu, mu=mu_outcome, sigma=sigma, observed=Y_data_, dims=\"obs\"\n", " )\n", "\n", " return model\n", "\n", "\n", "model = make_joint_model(X_trt, X_outcome, T_data, Y_data, coords)\n", "\n", "pm.model_to_graphviz(model)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Note how the two likelihood terms are fit simultaneously. \n", "\n", ":::{note}\n", "We are specifying the models in raw `PyMC` code for clarity, but we will bundle these methods into the neater `CausalPy` API below. \n", ":::" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Specifying the 2 Stage Model\n", "\n", "Here we allow for a function that takes the same inputs but fits two separate models. First we fit the treatment model then store the `idata_treatment` this xarray object stores the posterior estimates for the propensity score. We pass this through to a second outcome model where we proceed to take a random draw from the posterior and pass it through to the outcome regression via a spline component. This allows us to express any non-linearity in the treatment effect. Additionally it can be seen as a way to augment the outcome model.\n", "\n", "While theoretically the propensity score contains no extra information if we are already conditioning on $X$, practically the literature reports that the propensity improves the stability of the causal estimates achievable in Bayesian causal modelling. Additionally we might want to separate covariates for predicting the outcome and the treatment. In this case, there may be extra information derived in the treatment model that be used to inform the outcome model. " ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "clusterobs (4000) x betas_trt (3)\n", "\n", "obs (4000) x betas_trt (3)\n", "\n", "\n", "clusterobs (4000)\n", "\n", "obs (4000)\n", "\n", "\n", "clusterbetas_trt (3)\n", "\n", "betas_trt (3)\n", "\n", "\n", "\n", "X\n", "\n", "X\n", "~\n", "Data\n", "\n", "\n", "\n", "p\n", "\n", "p\n", "~\n", "Deterministic\n", "\n", "\n", "\n", "X->p\n", "\n", "\n", "\n", "\n", "\n", "t_pred\n", "\n", "t_pred\n", "~\n", "Bernoulli\n", "\n", "\n", "\n", "T\n", "\n", "T\n", "~\n", "Data\n", "\n", "\n", "\n", "t_pred->T\n", "\n", "\n", "\n", "\n", "\n", "p->t_pred\n", "\n", "\n", "\n", "\n", "\n", "beta_trt_std\n", "\n", "beta_trt_std\n", "~\n", "Normal\n", "\n", "\n", "\n", "beta_trt_\n", "\n", "beta_trt_\n", "~\n", "Deterministic\n", "\n", "\n", "\n", "beta_trt_std->beta_trt_\n", "\n", "\n", "\n", "\n", "\n", "beta_trt_->p\n", "\n", "\n", "\n", "\n", "\n", "alpha_trt\n", "\n", "alpha_trt\n", "~\n", "Normal\n", "\n", "\n", "\n", "alpha_trt->p\n", "\n", "\n", "\n", "\n", "\n" ], "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def make_treatment_model(\n", " X_trt,\n", " T_data,\n", " coords,\n", " priors={\n", " \"beta_\": [0, 1],\n", " \"beta_trt\": [0, 1],\n", " \"alpha_trt\": [0, 1],\n", " \"alpha_outcome\": [0, 1],\n", " },\n", " noncentred=True,\n", "):\n", " with pm.Model(coords=coords) as model_trt:\n", " X_data_trt = pm.Data(\"X\", X_trt, dims=(\"obs\", \"betas_trt\"))\n", " T_data_ = pm.Data(\"T\", T_data, dims=\"obs\")\n", "\n", " if noncentred:\n", " mu_beta_trt, sigma_beta_trt = priors[\"beta_trt\"]\n", " beta_trt_std = pm.Normal(\"beta_trt_std\", 0, 1, dims=\"betas_trt\")\n", " beta_trt = pm.Deterministic(\n", " \"beta_trt_\",\n", " mu_beta_trt + sigma_beta_trt * beta_trt_std,\n", " dims=\"betas_trt\",\n", " )\n", "\n", " else:\n", " beta_trt = pm.Normal(\n", " \"beta_trt_\",\n", " priors[\"beta_trt\"][0],\n", " priors[\"beta_trt\"][1],\n", " dims=\"betas_trt\",\n", " )\n", "\n", " alpha_trt = pm.Normal(\n", " \"alpha_trt\", priors[\"alpha_trt\"][0], priors[\"alpha_trt\"][1]\n", " )\n", " mu_trt = alpha_trt + pm.math.dot(X_data_trt, beta_trt)\n", " p = pm.Deterministic(\"p\", pm.math.invlogit(mu_trt), dims=\"obs\")\n", "\n", " pm.Bernoulli(\"t_pred\", p=p, observed=T_data_, dims=\"obs\")\n", " return model_trt\n", "\n", "\n", "def make_outcome_model(\n", " X_outcome,\n", " Y_data,\n", " coords,\n", " priors={\n", " \"beta_\": [0, 1],\n", " \"beta_trt\": [0, 1],\n", " \"alpha_trt\": [0, 1],\n", " \"alpha_outcome\": [0, 1],\n", " \"sigma\": 1,\n", " \"beta_ps\": [0, 1],\n", " },\n", " noncentred=True,\n", " spline_component=False,\n", " propensity_score_idata=None,\n", " normal_outcome=True,\n", " winsorize_boundary=0.0,\n", "):\n", " propensity_scores = az.extract(propensity_score_idata)[\"p\"]\n", " with pm.Model(coords=coords) as model_outcome:\n", " X_data_outcome = pm.Data(\"X_outcome\", X_outcome, dims=(\"obs\", \"betas\"))\n", " Y_data_ = pm.Data(\"Y\", Y_data, dims=\"obs\")\n", "\n", " if noncentred:\n", " mu_beta, sigma_beta = priors[\"beta_\"]\n", " beta_std = pm.Normal(\"beta_std\", 0, 1, dims=\"betas\")\n", " beta = pm.Deterministic(\n", " \"beta_\", mu_beta + sigma_beta * beta_std, dims=\"betas\"\n", " )\n", " else:\n", " beta = pm.Normal(\n", " \"beta_\", priors[\"beta_\"][0], priors[\"beta_\"][1], dims=\"betas\"\n", " )\n", "\n", " beta_ps = pm.Normal(\"beta_ps\", priors[\"beta_ps\"][0], priors[\"beta_ps\"][1])\n", "\n", " chosen = np.random.choice(range(propensity_scores.shape[1]))\n", " p = propensity_scores[:, chosen].values\n", " p = np.clip(p, winsorize_boundary, 1 - winsorize_boundary)\n", "\n", " alpha_outcome = pm.Normal(\n", " \"alpha_outcome\", priors[\"alpha_outcome\"][0], priors[\"alpha_outcome\"][1]\n", " )\n", " mu_outcome = alpha_outcome + pm.math.dot(X_data_outcome, beta) + beta_ps * p\n", "\n", " if spline_component:\n", " beta_ps_spline = pm.Normal(\n", " \"beta_ps_spline\", priors[\"beta_ps\"][0], priors[\"beta_ps\"][1], size=14\n", " )\n", " B = dmatrix(\n", " \"bs(ps, knots=knots, degree=3, include_intercept=True, lower_bound=0, upper_bound=1) - 1\",\n", " {\"ps\": p, \"knots\": np.linspace(0, 1, 10)},\n", " )\n", " B_f = np.asarray(B, order=\"F\")\n", " splines_summed = pm.Deterministic(\n", " \"spline_features\", pm.math.dot(B_f, beta_ps_spline.T), dims=\"obs\"\n", " )\n", " mu_outcome = (\n", " alpha_outcome + pm.math.dot(X_data_outcome, beta) + splines_summed\n", " )\n", "\n", " sigma = pm.HalfNormal(\"sigma\", priors[\"sigma\"])\n", "\n", " if normal_outcome:\n", " _ = pm.Normal(\"like\", mu_outcome, sigma, observed=Y_data_, dims=\"obs\")\n", " else:\n", " nu = pm.Exponential(\"nu\", lam=1 / 10)\n", " _ = pm.StudentT(\n", " \"like\", nu=nu, mu=mu_outcome, sigma=sigma, observed=Y_data_, dims=\"obs\"\n", " )\n", "\n", " return model_outcome\n", "\n", "\n", "def make_2step_model(\n", " X_trt,\n", " X_outcome,\n", " T_data,\n", " Y_data,\n", " coords,\n", " priors,\n", " spline_component=False,\n", " normal_outcome=True,\n", " winsorize_boundary=0.0,\n", "):\n", " treatment_model = make_treatment_model(X_trt, T_data, coords, priors)\n", " with treatment_model:\n", " idata_treatment = pm.sample_prior_predictive()\n", " idata_treatment.extend(pm.sample(**sampler_kwargs))\n", "\n", " outcome_model = make_outcome_model(\n", " X_outcome,\n", " Y_data,\n", " coords,\n", " priors,\n", " spline_component=spline_component,\n", " propensity_score_idata=idata_treatment,\n", " normal_outcome=normal_outcome,\n", " winsorize_boundary=winsorize_boundary,\n", " )\n", " with outcome_model:\n", " idata_outcome = pm.sample_prior_predictive()\n", " idata_outcome.extend(pm.sample(**sampler_kwargs))\n", "\n", " return idata_treatment, idata_outcome, treatment_model, outcome_model\n", "\n", "\n", "model_treatment = make_treatment_model(X_trt, T_data, coords)\n", "\n", "pm.model_to_graphviz(model_treatment)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Specifying a Simple Regression Model without Propensity Scores\n", "\n", "Now we specify a simple regression model which does not make use of the propensity score information. This model will be used to assess how much extra information is gleaned from the presence of the propensity score as covariate in our outcome model. " ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "def make_reg_model(\n", " X_outcome,\n", " Y_data,\n", " coords,\n", " priors={\n", " \"beta_\": [0, 1],\n", " \"alpha_outcome\": [0, 1],\n", " \"sigma\": 1,\n", " },\n", " noncentred=True,\n", "):\n", " with pm.Model(coords=coords) as reg_model:\n", " X_data_outcome = pm.Data(\"X_outcome\", X_outcome, dims=(\"obs\", \"betas\"))\n", " Y_data_ = pm.Data(\"Y\", Y_data, dims=\"obs\")\n", "\n", " if noncentred:\n", " mu_beta, sigma_beta = priors[\"beta_\"]\n", " beta_std = pm.Normal(\"beta_std\", 0, 1, dims=\"betas\")\n", " beta = pm.Deterministic(\n", " \"beta_\", mu_beta + sigma_beta * beta_std, dims=\"betas\"\n", " )\n", " else:\n", " beta = pm.Normal(\n", " \"beta_\", priors[\"beta_\"][0], priors[\"beta_\"][1], dims=\"betas\"\n", " )\n", " alpha_outcome = pm.Normal(\n", " \"alpha_outcome\", priors[\"alpha_outcome\"][0], priors[\"alpha_outcome\"][1]\n", " )\n", " mu_outcome = alpha_outcome + pm.math.dot(X_data_outcome, beta)\n", " sigma = pm.HalfNormal(\"sigma\", priors[\"sigma\"])\n", "\n", " _ = pm.Normal(\"like\", mu_outcome, sigma, observed=Y_data_, dims=\"obs\")\n", "\n", " idata = pm.sample(**sampler_kwargs)\n", "\n", " return reg_model, idata" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Putting it all Together\n", "\n", "We are now in a position to fit both joint and modular (2-stage) models to our simulated data. We are seeking to assess how the different approaches to incorporating propensity score information impacts the accuracy of the treatment effect estimate. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ ":::{note}\n", "We are using this snippet of code to pass the posterior distribution of the propensity score through to the outcome model and have it be sampled in the MCMC process of the outcome model. \n", "\n", "```\n", "chosen = np.random.choice(range(propensity_scores.shape[1]))\n", "p = propensity_scores[:, chosen].values\n", "```\n", "\n", "This allows us to modularise the the fitting process but retain the useful information stored in the propensity score. \n", ":::" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "tags": [ "hide-output" ] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Initializing NUTS using jitter+adapt_diag...\n", "Multiprocess sampling (4 chains in 4 jobs)\n", "NUTS: [beta_trt_std, beta_std, beta_ps, alpha_trt, alpha_outcome, sigma]\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "f534d219404c427e91090de2bf6eac01", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Output()" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n", " return 0.5 * np.dot(x, v_out)\n" ] }, { "data": { "text/html": [ "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 80 seconds.\n",
      "Sampling: [alpha_trt, beta_trt_std, t_pred]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_trt_std, alpha_trt]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "87015075e2d7484aa8e841099cb71aec",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 20 seconds.\n",
      "Sampling: [alpha_outcome, beta_ps, beta_std, like, sigma]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, beta_ps, alpha_outcome, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "06654bdc20e84c09aa0193acf2d6f2fc",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n",
      "  return 0.5 * np.dot(x, v_out)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 16 seconds.\n",
      "Sampling: [alpha_trt, beta_trt_std, t_pred]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_trt_std, alpha_trt]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "11dd78ec554d459184568c6d6ae4688d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 18 seconds.\n",
      "Sampling: [alpha_outcome, beta_ps, beta_ps_spline, beta_std, like, sigma]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, beta_ps, alpha_outcome, beta_ps_spline, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "53f5b8b3fcc34f54aab4db78e5de00de",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 37 seconds.\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, alpha_outcome, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1223050a347d4a9c8d270e2887fab910",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n",
      "  return 0.5 * np.dot(x, v_out)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 12 seconds.\n"
     ]
    }
   ],
   "source": [
    "priors = {\n",
    "    \"beta_\": [0, 3],\n",
    "    \"beta_trt\": [0, 1],\n",
    "    \"alpha_trt\": [0, 1],\n",
    "    \"alpha_outcome\": [0, 1],\n",
    "    \"sigma\": 1,\n",
    "    \"beta_ps\": [0, 1],\n",
    "}\n",
    "\n",
    "joint_model = make_joint_model(X_trt, X_outcome, T_data, Y_data, coords, priors=priors)\n",
    "\n",
    "with joint_model:\n",
    "    idata_joint = pm.sample(**sampler_kwargs)\n",
    "\n",
    "(\n",
    "    idata_treatment_2s_joint,\n",
    "    idata_outcome_2s_joint,\n",
    "    treatment_model_joint,\n",
    "    outcome_model_joint,\n",
    ") = make_2step_model(\n",
    "    X_trt, X_outcome, T_data, Y_data, coords, priors, spline_component=False\n",
    ")\n",
    "\n",
    "(\n",
    "    idata_treatment_2s_joint_spline,\n",
    "    idata_outcome_2s_joint_spline,\n",
    "    treatment_model_joint_spline,\n",
    "    outcome_model_joint_spline,\n",
    ") = make_2step_model(\n",
    "    X_trt, X_outcome, T_data, Y_data, coords, priors, spline_component=True\n",
    ")\n",
    "\n",
    "reg_model, idata_outcome_simple_reg = make_reg_model(X_outcome, Y_data, coords)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = az.plot_forest(\n",
    "    [\n",
    "        idata_outcome_2s_joint,\n",
    "        idata_outcome_2s_joint_spline,\n",
    "        idata_joint,\n",
    "        idata_outcome_simple_reg,\n",
    "    ],\n",
    "    var_names=[\"beta_\"],\n",
    "    model_names=[\"2 Stage\", \"2 Stage + Spline\", \"1 Stage\", \"Simple Regression\"],\n",
    "    combined=True,\n",
    "    figsize=(10, 5),\n",
    ")\n",
    "\n",
    "ax[0].axvline(2, label=\"True Treatment Value\", color=\"k\")\n",
    "ax[0].set_title(\"Comparing Joint and 2 Stage Propensity Score Parameter Fits\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
meansdhdi_3%hdi_97%r_hat
1-stage-modelalpha_trt0.0000.021-0.0400.0411.0
beta_[trt]2.3140.0572.2062.4191.0
beta_[x1]1.2960.0701.1671.4281.0
beta_ps-15.2970.294-15.840-14.7381.0
alpha_outcome8.5070.1618.2168.8211.0
2-stage-modelbeta_[trt]2.0580.1891.6962.3981.0
beta_[x1]1.1550.0411.0791.2351.0
alpha_outcome3.0670.0602.9533.1761.0
beta_ps-4.1470.210-4.541-3.7591.0
2-stage-model_splinebeta_[trt]1.8240.1791.4902.1611.0
beta_[x1]1.1620.0401.0871.2361.0
alpha_outcome1.0070.2930.4411.5441.0
beta_ps-0.0090.983-1.7971.8801.0
Simple Regressionbeta_[trt]-1.3080.085-1.464-1.1441.0
beta_[x1]1.1070.0431.0291.1901.0
alpha_outcome2.6650.0602.5492.7731.0
\n",
       "
"
      ],
      "text/plain": [
       "                                      mean     sd  hdi_3%  hdi_97%  r_hat\n",
       "1-stage-model        alpha_trt       0.000  0.021  -0.040    0.041    1.0\n",
       "                     beta_[trt]      2.314  0.057   2.206    2.419    1.0\n",
       "                     beta_[x1]       1.296  0.070   1.167    1.428    1.0\n",
       "                     beta_ps       -15.297  0.294 -15.840  -14.738    1.0\n",
       "                     alpha_outcome   8.507  0.161   8.216    8.821    1.0\n",
       "2-stage-model        beta_[trt]      2.058  0.189   1.696    2.398    1.0\n",
       "                     beta_[x1]       1.155  0.041   1.079    1.235    1.0\n",
       "                     alpha_outcome   3.067  0.060   2.953    3.176    1.0\n",
       "                     beta_ps        -4.147  0.210  -4.541   -3.759    1.0\n",
       "2-stage-model_spline beta_[trt]      1.824  0.179   1.490    2.161    1.0\n",
       "                     beta_[x1]       1.162  0.040   1.087    1.236    1.0\n",
       "                     alpha_outcome   1.007  0.293   0.441    1.544    1.0\n",
       "                     beta_ps        -0.009  0.983  -1.797    1.880    1.0\n",
       "Simple Regression    beta_[trt]     -1.308  0.085  -1.464   -1.144    1.0\n",
       "                     beta_[x1]       1.107  0.043   1.029    1.190    1.0\n",
       "                     alpha_outcome   2.665  0.060   2.549    2.773    1.0"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_estimate = pd.concat(\n",
    "    {\n",
    "        \"1-stage-model\": az.summary(\n",
    "            idata_joint, var_names=[\"alpha_trt\", \"beta_\", \"beta_ps\", \"alpha_outcome\"]\n",
    "        ),\n",
    "        \"2-stage-model\": az.summary(\n",
    "            idata_outcome_2s_joint, var_names=[\"beta_\", \"alpha_outcome\", \"beta_ps\"]\n",
    "        ),\n",
    "        \"2-stage-model_spline\": az.summary(\n",
    "            idata_outcome_2s_joint_spline,\n",
    "            var_names=[\"beta_\", \"alpha_outcome\", \"beta_ps\"],\n",
    "        ),\n",
    "        \"Simple Regression\": az.summary(\n",
    "            idata_outcome_simple_reg,\n",
    "            var_names=[\"beta_\", \"alpha_outcome\"],\n",
    "        ),\n",
    "    }\n",
    ")\n",
    "compare_estimate[[\"mean\", \"sd\", \"hdi_3%\", \"hdi_97%\", \"r_hat\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here the models fail to recover substantially similar and correct results, in particular the simple regression model is widely off. However the 2-stage models seem to perform better than the joint model specification. This is interesting and demonstrates a key property of propensity scores in the Bayesian setting. Propensity scores are useful correctives within a regression context but we need to be careful how the model is specified.\n",
    "\n",
    "### The Problem of Feedback\n",
    "The issue here is sometimes called Bayesian feedback or \"collider bias via the likelihood\" {cite:p}`GriffithCollider`, and it's a key issue when trying to build joint models for causal inference in the Bayesian paradigm. Because we have fit the outcome and the treatment models simultaneously, and this means that the outcome can influence the posterior distribution of the parameters $\\beta$ in the treatment model and it violates the idea of design-before-analysis. We have here an apparent example of a slight bias due to this effect.  The two stage modular approach seems to better recover the treatment effect reported in the literature and avoids the risk of collider bias i.e. in the modular implementation we are able to use the propensity score to adjust for accuracy and compensate for the missing variables `x2` and `x1`. \n",
    "\n",
    "\n",
    "**💡 Key Take-away:** With an underspecified outcome model, we may use a well specified propensity score for adjusting the model to retrieve accurate treatment effect estimates. However, this tends to breakdown if we have estimated both propensity score and outcome in a joint bayesian model due to feedback effects. The solution is to use the propensity score in a 2 stage fashion. \n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "clusterobs (4000) x betas (2)\n",
       "\n",
       "obs (4000) x betas (2)\n",
       "\n",
       "\n",
       "clusterobs (4000)\n",
       "\n",
       "obs (4000)\n",
       "\n",
       "\n",
       "clusterbetas (2)\n",
       "\n",
       "betas (2)\n",
       "\n",
       "\n",
       "cluster14\n",
       "\n",
       "14\n",
       "\n",
       "\n",
       "\n",
       "X_outcome\n",
       "\n",
       "X_outcome\n",
       "~\n",
       "Data\n",
       "\n",
       "\n",
       "\n",
       "like\n",
       "\n",
       "like\n",
       "~\n",
       "Normal\n",
       "\n",
       "\n",
       "\n",
       "X_outcome->like\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "Y\n",
       "\n",
       "Y\n",
       "~\n",
       "Data\n",
       "\n",
       "\n",
       "\n",
       "like->Y\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "spline_features\n",
       "\n",
       "spline_features\n",
       "~\n",
       "Deterministic\n",
       "\n",
       "\n",
       "\n",
       "spline_features->like\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "beta_\n",
       "\n",
       "beta_\n",
       "~\n",
       "Deterministic\n",
       "\n",
       "\n",
       "\n",
       "beta_->like\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "beta_std\n",
       "\n",
       "beta_std\n",
       "~\n",
       "Normal\n",
       "\n",
       "\n",
       "\n",
       "beta_std->beta_\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "sigma\n",
       "\n",
       "sigma\n",
       "~\n",
       "HalfNormal\n",
       "\n",
       "\n",
       "\n",
       "sigma->like\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "beta_ps\n",
       "\n",
       "beta_ps\n",
       "~\n",
       "Normal\n",
       "\n",
       "\n",
       "\n",
       "alpha_outcome\n",
       "\n",
       "alpha_outcome\n",
       "~\n",
       "Normal\n",
       "\n",
       "\n",
       "\n",
       "alpha_outcome->like\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "beta_ps_spline\n",
       "\n",
       "beta_ps_spline\n",
       "~\n",
       "Normal\n",
       "\n",
       "\n",
       "\n",
       "beta_ps_spline->spline_features\n",
       "\n",
       "\n",
       "\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       ""
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pm.model_to_graphviz(outcome_model_joint_spline)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Propensity Score Quantiles - Joint Model\n",
    "\n",
    "We can see how the different model specifications have yielded distinct propensity score estimates - as the joint specification seems to compensate for missing covariates in the outcome model by adjusting the propensity score latent in the treatment model too. We can see the differences in the quantiles to highlight a numeric difference in the propensity score distributions between the two models."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.224, 0.308, 0.38 , 0.442, 0.502, 0.563, 0.624, 0.691, 0.769])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata_joint[\"posterior\"][\"p\"].quantile(\n",
    "    [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]\n",
    ").round(3).values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Propensity Score Quantiles - 2 Stage Modular Model\n",
    "\n",
    "The range an position of these quantiles is vastly different than the joint model specification. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.   , 0.001, 0.014, 0.11 , 0.506, 0.886, 0.986, 0.999, 1.   ])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata_treatment_2s_joint[\"posterior\"][\"p\"].quantile(\n",
    "    [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]\n",
    ").round(3).values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Comparing Propensity Score Skew\n",
    "\n",
    "We have seen how the treatment effect reported by both models differ and that the joint model exhibits a bias away from the true treatment effect. But we might want to see how this bias manifests in the propensity score distribution. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def compare_propensity_dists(idata_2s, idata_1s):\n",
    "    fig, ax = plt.subplots(figsize=(10, 4))\n",
    "    for i in range(100):\n",
    "        s2 = idata_2s[\"posterior\"].stack(z=(\"chain\", \"draw\"))[\"p\"][:, i]\n",
    "        s1 = idata_1s[\"posterior\"].stack(z=(\"chain\", \"draw\"))[\"p\"][:, i]\n",
    "        if i == 0:\n",
    "            ax.hist(\n",
    "                s2,\n",
    "                alpha=0.1,\n",
    "                color=\"orange\",\n",
    "                label=\"Propensity Scores 2-stage Estimation\",\n",
    "            )\n",
    "            # Pivoted to compare shape\n",
    "            ax.hist(\n",
    "                1 - s1,\n",
    "                alpha=0.1,\n",
    "                color=\"blue\",\n",
    "                label=\"Propensity Scores 1-stage Estimation\",\n",
    "            )\n",
    "        else:\n",
    "            ax.hist(s2, alpha=0.01, color=\"orange\")\n",
    "            # Pivoted to compare shape\n",
    "            ax.hist(1 - s1, alpha=0.01, color=\"blue\")\n",
    "    ax.legend()\n",
    "    ax.set_title(\n",
    "        \"Comparing Propensity Distributions \\n Two-stage and Joint Estimation routines\"\n",
    "    )\n",
    "\n",
    "\n",
    "compare_propensity_dists(idata_treatment_2s_joint, idata_joint)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "These are radically different models due to the feedback mechanism. How does this phenomena play out in some real world examples?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "spline_features = az.extract(idata_outcome_2s_joint_spline)[\"spline_features\"]\n",
    "\n",
    "propensity_scores = az.extract(idata_treatment_2s_joint_spline)[\"p\"]\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(10, 5))\n",
    "for i in range(100):\n",
    "    temp = pd.DataFrame(\n",
    "        {\"prop_score\": propensity_scores[:, i], \"spline\": spline_features[:, i]}\n",
    "    )\n",
    "    temp.sort_values(\"prop_score\", inplace=True)\n",
    "    ax.plot(temp[\"prop_score\"], temp[\"spline\"], alpha=0.01, color=\"blue\")\n",
    "\n",
    "temp = pd.DataFrame(\n",
    "    {\n",
    "        \"prop_score\": propensity_scores.mean(axis=1),\n",
    "        \"spline\": spline_features.mean(axis=1),\n",
    "    }\n",
    ")\n",
    "temp.sort_values(\"prop_score\", inplace=True)\n",
    "ax.plot(temp[\"prop_score\"], temp[\"spline\"], color=\"k\", label=\"Expected Value\")\n",
    "ax.set_title(\"Additive Spline Effect on the Propensity Score\")\n",
    "ax.legend()\n",
    "ax.set_ylabel(\"Spline Feature Contribution\")\n",
    "ax.set_xlabel(\"Propensity Score\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    ":::{note}\n",
    "The idea of allowing a spline component to contribute to the `mu_outcome` or expectation of our model, is that in some cases there might be a non-linear relationship between the propensity for treatment and the outcome interest. \n",
    "\n",
    "$$ \\mu = \\alpha + X\\beta + f(p) $$\n",
    "\n",
    "Incorporating the spline function of `p` grants our model this kind of flexibility to account for different response categories across levels of the propensity score. \n",
    ":::"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Causal Estimate with Do-Operator\n",
    "\n",
    "We can also confirm the model implications through counterfactual imputation. This ties the Bayesian setting back to the {term}`potential outcome` framework. The fundamental problem of causal inference, when seen as a missing data problem allows us to derive causal estimands through imputation of the potential outcomes. Here we \"push forward\" the posterior predictive distribution for $Y$ under different treatment settings. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_outcome_trt = X_outcome.copy()\n",
    "X_outcome_trt[:, 0] = 1\n",
    "\n",
    "X_outcome_ntrt = X_outcome.copy()\n",
    "X_outcome_ntrt[:, 0] = 0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First we specify our counterfactual input data. Then we push them through the joint model distribution using the do-operator in `PyMC` to sample from the posterior predictive distribution giving us sample of the potential outcomes $Y(1), Y(0)$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling: [like]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "820355aedb654c76b1ecced9ed028540",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling: [like]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0aee7342cdb2406abfc0a4134de44d15",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "with pm.do(\n",
    "    joint_model,\n",
    "    {\"T\": np.ones(len(df1), dtype=np.int32), \"X_outcome\": X_outcome_trt},\n",
    "    prune_vars=True,\n",
    ") as treatment_model:\n",
    "    idata_trt = pm.sample_posterior_predictive(idata_joint, var_names=[\"like\", \"p\"])\n",
    "\n",
    "with pm.do(\n",
    "    joint_model,\n",
    "    {\"T\": np.zeros(len(df1), dtype=np.int32), \"X_outcome\": X_outcome_ntrt},\n",
    "    prune_vars=True,\n",
    ") as ntreatment_model:\n",
    "    idata_ntrt = pm.sample_posterior_predictive(idata_joint, var_names=[\"like\", \"p\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For sake of illustration we calculate the mean value for $Y(1)$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.1565468847153166"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata_trt[\"posterior_predictive\"][\"like\"].mean().item()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The mean value for $Y(0)$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8421930047703092"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata_ntrt[\"posterior_predictive\"][\"like\"].mean().item()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "and their difference, which is the causal estimand of interest."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2.314353879945007"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(\n",
    "    idata_trt[\"posterior_predictive\"][\"like\"].mean().item()\n",
    "    - idata_ntrt[\"posterior_predictive\"][\"like\"].mean().item()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this way we can impute potential outcomes gain insight into any variety of causal estimands we care to calculate. In this case, we have re-derived the insight that the joint model yields a biased treatment effect estimate. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Nets Example\n",
    "\n",
    "Next we'll asses a data set used by [Andrew Heiss](https://www.andrewheiss.com/blog/2021/12/20/fully-bayesian-ate-iptw/) to demonstrate propensity score methods with `brms`. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
idnetnet_nummalaria_riskincomehealthhouseholdeligibletemperatureresistancetrtoutcome
01True133781562False21.159133
12False042974574False26.573042
23False080502153False25.665080
34True134671205True21.346134
45False044728175False19.254044
\n",
       "
"
      ],
      "text/plain": [
       "   id    net  net_num  malaria_risk  income  health  household  eligible  \\\n",
       "0   1   True        1            33     781      56          2     False   \n",
       "1   2  False        0            42     974      57          4     False   \n",
       "2   3  False        0            80     502      15          3     False   \n",
       "3   4   True        1            34     671      20          5      True   \n",
       "4   5  False        0            44     728      17          5     False   \n",
       "\n",
       "   temperature  resistance  trt  outcome  \n",
       "0         21.1          59    1       33  \n",
       "1         26.5          73    0       42  \n",
       "2         25.6          65    0       80  \n",
       "3         21.3          46    1       34  \n",
       "4         19.2          54    0       44  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nets_df = cp.load_data(\"nets\")\n",
    "nets_df[\"trt\"] = nets_df[\"net_num\"]\n",
    "nets_df[\"outcome\"] = nets_df[\"malaria_risk\"]\n",
    "nets_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "tags": [
     "hide-output"
    ]
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_trt_std, beta_std, beta_ps, alpha_trt, alpha_outcome, sigma, nu]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "18df0f5e2e584ff5be504150fb69322d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 1_000 draw iterations (8_000 + 4_000 draws total) took 17 seconds.\n",
      "Sampling: [alpha_trt, beta_trt_std, t_pred]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_trt_std, alpha_trt]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6f09c66275bc456b82ef06f65a2e5eb5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 14 seconds.\n",
      "Sampling: [alpha_outcome, beta_ps, beta_std, like, nu, sigma]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, beta_ps, alpha_outcome, sigma, nu]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "74ba5d8da4674f0a919cdb13ebff7db7",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 15 seconds.\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, alpha_outcome, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "199a5dbd9da44b90bc45eeb5d6eb3114",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n",
      "  return 0.5 * np.dot(x, v_out)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 11 seconds.\n"
     ]
    }
   ],
   "source": [
    "coords = {\n",
    "    \"betas\": [\"trt\", \"income\"],\n",
    "    \"betas_trt\": [\"income\", \"temperature\", \"health\"],\n",
    "    \"obs\": range(nets_df.shape[0]),\n",
    "}\n",
    "\n",
    "# Process and Standardise Inputs\n",
    "N = nets_df.shape[0]\n",
    "X_trt = nets_df[[\"income\", \"temperature\", \"health\"]].values\n",
    "X_trt = (X_trt - X_trt.mean(axis=0)) / X_trt.std(axis=0)\n",
    "X_outcome = nets_df[[\"trt\", \"income\"]].values\n",
    "X_outcome = (X_outcome - X_outcome.mean(axis=0)) / X_outcome.std(axis=0)\n",
    "T_data = nets_df[\"trt\"].values\n",
    "X_outcome[:, 0] = T_data\n",
    "Y_data = nets_df[\"outcome\"].values\n",
    "\n",
    "priors = {\n",
    "    \"beta_\": [0, 1],\n",
    "    \"beta_trt\": [0, 1],\n",
    "    \"alpha_trt\": [0, 1],\n",
    "    \"alpha_outcome\": [40, 30],\n",
    "    \"sigma\": 15,\n",
    "    \"beta_ps\": [0, 1],\n",
    "}\n",
    "net_model = make_joint_model(\n",
    "    X_trt, X_outcome, T_data, Y_data, coords, priors=priors, normal_outcome=False\n",
    ")\n",
    "\n",
    "with net_model:\n",
    "    idata_net = pm.sample(tune=2000, target_accept=0.98)\n",
    "\n",
    "idata_treatment_2s_net, idata_outcome_2s_net, treatment_model_net, outcome_model_net = (\n",
    "    make_2step_model(\n",
    "        X_trt, X_outcome, T_data, Y_data, coords, priors=priors, normal_outcome=False\n",
    "    )\n",
    ")\n",
    "\n",
    "reg_model_nets, idata_outcome_simple_reg_nets = make_reg_model(\n",
    "    X_outcome, Y_data, coords\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = az.plot_forest(\n",
    "    [idata_outcome_2s_net, idata_net, idata_outcome_simple_reg_nets],\n",
    "    var_names=[\"beta_\"],\n",
    "    model_names=[\"2 Stage\", \"1 Stage\", \"Simple Regression\"],\n",
    "    combined=True,\n",
    "    figsize=(10, 4),\n",
    ")\n",
    "\n",
    "ax[0].axvline(-10, label=\"True Treatment Value\", color=\"k\")\n",
    "ax[0].set_title(\"Comparing Joint and 2 Stage Propensity Score Parameter Fits\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As before we have used both model specifications to derive estimates for the treatment effect. In this case we have allowed the outcome model access to only a single `income` predictor. And while both models seem to approximtely recover the reported -10 treatment estimate with a large degree of uncertainty. The modular 2 stage estimates pulls away from the joint model estimate.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
meansdhdi_3%hdi_97%r_hat
1-stage-modelalpha_trt-0.2610.052-0.358-0.1651.0
beta_[trt]-9.9330.262-10.410-9.4401.0
beta_[income]-10.0970.221-10.503-9.6801.0
beta_ps-16.1940.654-17.454-15.0041.0
alpha_outcome46.5800.39745.84147.3171.0
2-stage-modelbeta_[trt]-10.0530.316-10.640-9.4751.0
beta_[income]-10.5930.192-10.947-10.2321.0
alpha_outcome42.2020.41541.41842.9761.0
beta_ps-7.1460.938-8.913-5.4271.0
Simple Regressionbeta_[trt]-8.5340.338-9.198-7.9201.0
beta_[income]-11.5150.169-11.831-11.1931.0
alpha_outcome37.8320.21637.43938.2551.0
\n",
       "
"
      ],
      "text/plain": [
       "                                   mean     sd  hdi_3%  hdi_97%  r_hat\n",
       "1-stage-model     alpha_trt      -0.261  0.052  -0.358   -0.165    1.0\n",
       "                  beta_[trt]     -9.933  0.262 -10.410   -9.440    1.0\n",
       "                  beta_[income] -10.097  0.221 -10.503   -9.680    1.0\n",
       "                  beta_ps       -16.194  0.654 -17.454  -15.004    1.0\n",
       "                  alpha_outcome  46.580  0.397  45.841   47.317    1.0\n",
       "2-stage-model     beta_[trt]    -10.053  0.316 -10.640   -9.475    1.0\n",
       "                  beta_[income] -10.593  0.192 -10.947  -10.232    1.0\n",
       "                  alpha_outcome  42.202  0.415  41.418   42.976    1.0\n",
       "                  beta_ps        -7.146  0.938  -8.913   -5.427    1.0\n",
       "Simple Regression beta_[trt]     -8.534  0.338  -9.198   -7.920    1.0\n",
       "                  beta_[income] -11.515  0.169 -11.831  -11.193    1.0\n",
       "                  alpha_outcome  37.832  0.216  37.439   38.255    1.0"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_estimate = pd.concat(\n",
    "    {\n",
    "        \"1-stage-model\": az.summary(\n",
    "            idata_net,\n",
    "            var_names=[\"alpha_trt\", \"beta_\", \"beta_ps\", \"alpha_outcome\"],\n",
    "        ),\n",
    "        \"2-stage-model\": az.summary(\n",
    "            idata_outcome_2s_net, var_names=[\"beta_\", \"alpha_outcome\", \"beta_ps\"]\n",
    "        ),\n",
    "        \"Simple Regression\": az.summary(\n",
    "            idata_outcome_simple_reg_nets, var_names=[\"beta_\", \"alpha_outcome\"]\n",
    "        ),\n",
    "    }\n",
    ")\n",
    "compare_estimate[[\"mean\", \"sd\", \"hdi_3%\", \"hdi_97%\", \"r_hat\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This kind of difference need not be very concerning but we should check if the bias stems from a difference in latent propensity scores as before. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.181, 0.249, 0.31 , 0.369, 0.43 , 0.5  , 0.571, 0.643, 0.727])"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata_net[\"posterior\"][\"p\"].quantile(\n",
    "    [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]\n",
    ").round(3).values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The quantiles of the propensity distributions across both models seem different. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.239, 0.283, 0.317, 0.349, 0.379, 0.412, 0.449, 0.492, 0.556])"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idata_treatment_2s_net[\"posterior\"][\"p\"].quantile(\n",
    "    [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]\n",
    ").round(3).values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "compare_propensity_dists(idata_treatment_2s_net, idata_net)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here we see some divergence between the propensity score estimates indicating that the regression adjustment approach in the 2 stage outcome model is correcting for bias in the joint-distribution. However both credible intervals contain the reported treatment effect of -10 so the skew is perhaps less concerning. This is despite the fact that we removed useful predictors `temperature`, `health` from the outcome model specification. The model leans on the information contained in the propensity score and weights the `beta_ps` information appropriately. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### LaLonde Example\n",
    "\n",
    "The Lalonde Data set is famous because it highlights a problem with naive causal contrasts. It is discussed by Angrist and Pischke in their _Mostly Harmless Econometrics_ as an example of how regression controls can tolerably address selection effects in a way similar to propensity score weighting. So we should hope the a well specified outcome model can identify the treatment effects plausibly here too. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
rownamestreatageeducracemarriednodegreere74re75re78hispanwhite
0NSW113711black110.00.09930.0460FalseFalse
1NSW21229hispan010.00.03595.8940TrueFalse
2NSW313012black000.00.024909.4500FalseFalse
3NSW412711black010.00.07506.1460FalseFalse
4NSW51338black010.00.0289.7899FalseFalse
\n",
       "
"
      ],
      "text/plain": [
       "  rownames  treat  age  educ    race  married  nodegree  re74  re75  \\\n",
       "0     NSW1      1   37    11   black        1         1   0.0   0.0   \n",
       "1     NSW2      1   22     9  hispan        0         1   0.0   0.0   \n",
       "2     NSW3      1   30    12   black        0         0   0.0   0.0   \n",
       "3     NSW4      1   27    11   black        0         1   0.0   0.0   \n",
       "4     NSW5      1   33     8   black        0         1   0.0   0.0   \n",
       "\n",
       "         re78  hispan  white  \n",
       "0   9930.0460   False  False  \n",
       "1   3595.8940    True  False  \n",
       "2  24909.4500   False  False  \n",
       "3   7506.1460   False  False  \n",
       "4    289.7899   False  False  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lalonde = df = cp.load_data(\"lalonde\")\n",
    "lalonde[[\"hispan\", \"white\"]] = pd.get_dummies(lalonde[\"race\"], drop_first=True)\n",
    "lalonde.dropna(inplace=True)\n",
    "lalonde.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "treat\n",
       "0           NaN\n",
       "1   -635.026212\n",
       "Name: re78, dtype: float64"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lalonde.groupby(\"treat\")[\"re78\"].mean().diff()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Naive group difference suggests a negative effect. Lets see how our two models work when we remove predictors from the propensity model?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "tags": [
     "hide-output"
    ]
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_trt_, beta_, beta_ps, alpha_trt, alpha_outcome, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2f6936bc6f8f4bbd8c3f867511e7027c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n",
      "  return 0.5 * np.dot(x, v_out)\n",
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n",
      "  return 0.5 * np.dot(x, v_out)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 5_000 tune and 1_000 draw iterations (20_000 + 4_000 draws total) took 6 seconds.\n",
      "Sampling: [alpha_trt, beta_trt_std, t_pred]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_trt_std, alpha_trt]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4fc603f50a0c44cca30c12a5cfea446f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 13 seconds.\n",
      "Sampling: [alpha_outcome, beta_ps, beta_ps_spline, beta_std, like, sigma]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, beta_ps, alpha_outcome, beta_ps_spline, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3cb4afa0b8f442ccb2a4239fda999500",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 14 seconds.\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, alpha_outcome, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "50878c7b5c59437682a0e3c838998305",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n",
      "  return 0.5 * np.dot(x, v_out)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n",
      "  return 0.5 * np.dot(x, v_out)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 11 seconds.\n"
     ]
    }
   ],
   "source": [
    "coords = {\n",
    "    \"betas\": [\"treat\", \"nodegree\", \"married\"],\n",
    "    \"betas_trt\": [\"age\", \"educ\", \"hispan\", \"white\", \"married\", \"nodegree\"],\n",
    "    \"obs\": range(lalonde.shape[0]),\n",
    "}\n",
    "\n",
    "N = lalonde.shape[0]\n",
    "X_trt = (\n",
    "    lalonde[[\"age\", \"educ\", \"hispan\", \"white\", \"married\", \"nodegree\"]]\n",
    "    .astype(np.int32)\n",
    "    .values\n",
    ")\n",
    "X_trt = (X_trt - X_trt.mean(axis=0)) / X_trt.std(axis=0)\n",
    "\n",
    "X_outcome = lalonde[[\"treat\", \"nodegree\", \"married\"]].astype(np.int32).values\n",
    "# X_outcome = (X_outcome - X_outcome.mean()) / X_outcome.std()\n",
    "T_data = lalonde[\"treat\"].values\n",
    "Y_data = lalonde[\"re78\"].values\n",
    "\n",
    "\n",
    "priors = {\n",
    "    \"beta_\": [0, 4000],\n",
    "    \"beta_trt\": [0, 1],\n",
    "    \"alpha_trt\": [0, 1],\n",
    "    \"alpha_outcome\": [2000, 500],\n",
    "    \"sigma\": 500,\n",
    "    \"beta_ps\": [0, 30],\n",
    "}\n",
    "\n",
    "lalonde_model = make_joint_model(\n",
    "    X_trt, X_outcome, T_data, Y_data, coords, priors, noncentred=False\n",
    ")\n",
    "\n",
    "with lalonde_model:\n",
    "    idata_lalonde = pm.sample(tune=5000)\n",
    "\n",
    "(\n",
    "    idata_treatment_2s_lalonde,\n",
    "    idata_outcome_2s_lalonde,\n",
    "    treatment_model_lalonde,\n",
    "    outcome_model_lalonde,\n",
    ") = make_2step_model(\n",
    "    X_trt,\n",
    "    X_outcome,\n",
    "    T_data,\n",
    "    Y_data,\n",
    "    coords,\n",
    "    priors=priors,\n",
    "    spline_component=True,\n",
    "    winsorize_boundary=0.1,\n",
    ")\n",
    "\n",
    "reg_model_lalonde, idata_outcome_simple_reg_lalonde = make_reg_model(\n",
    "    X_outcome, Y_data, coords, priors=priors\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = az.plot_forest(\n",
    "    [idata_outcome_2s_lalonde, idata_lalonde, idata_outcome_simple_reg_lalonde],\n",
    "    var_names=[\"beta_\", \"sigma\"],\n",
    "    model_names=[\"2 Stage\", \"1 Stage\", \"Simple Regression\"],\n",
    "    combined=True,\n",
    "    figsize=(10, 4),\n",
    ")\n",
    "# Experimental benchmark between 1600 - 1800\n",
    "ax[0].axvline(1700, color=\"black\")\n",
    "ax[0].set_title(\"Comparing Joint and 2 Stage Propensity Score Parameter Fits\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
meansdhdi_3%hdi_97%r_hat
1-stage-modelalpha_trt-1.3600.136-1.607-1.0961.0
beta_[treat]1596.367592.252522.0042698.8411.0
beta_[nodegree]-478.468494.181-1411.118431.6501.0
beta_[married]3941.883521.1932935.7814905.1491.0
beta_ps1.51530.782-59.15956.7831.0
alpha_outcome4318.250369.2883624.1245022.5751.0
sigma6567.379152.7896262.9056837.3761.0
2-stage-modelbeta_[treat]1588.023560.154606.8422705.4021.0
beta_[nodegree]-459.243493.565-1378.890456.6111.0
beta_[married]3938.877513.1012988.6124920.5451.0
beta_ps-0.04129.752-56.00356.8091.0
alpha_outcome4311.600368.0823627.1735011.7841.0
sigma6569.193153.7456279.5936855.4071.0
Simple Regressionbeta_[treat]1582.104582.999493.4422672.6451.0
beta_[nodegree]-454.568492.429-1360.717461.7601.0
beta_[married]3926.351519.7442930.8134873.1111.0
alpha_outcome4320.328368.7533628.0374996.0101.0
sigma6568.130149.6996293.1936860.3011.0
\n",
       "
"
      ],
      "text/plain": [
       "                                       mean       sd    hdi_3%   hdi_97%  \\\n",
       "1-stage-model     alpha_trt          -1.360    0.136    -1.607    -1.096   \n",
       "                  beta_[treat]     1596.367  592.252   522.004  2698.841   \n",
       "                  beta_[nodegree]  -478.468  494.181 -1411.118   431.650   \n",
       "                  beta_[married]   3941.883  521.193  2935.781  4905.149   \n",
       "                  beta_ps             1.515   30.782   -59.159    56.783   \n",
       "                  alpha_outcome    4318.250  369.288  3624.124  5022.575   \n",
       "                  sigma            6567.379  152.789  6262.905  6837.376   \n",
       "2-stage-model     beta_[treat]     1588.023  560.154   606.842  2705.402   \n",
       "                  beta_[nodegree]  -459.243  493.565 -1378.890   456.611   \n",
       "                  beta_[married]   3938.877  513.101  2988.612  4920.545   \n",
       "                  beta_ps            -0.041   29.752   -56.003    56.809   \n",
       "                  alpha_outcome    4311.600  368.082  3627.173  5011.784   \n",
       "                  sigma            6569.193  153.745  6279.593  6855.407   \n",
       "Simple Regression beta_[treat]     1582.104  582.999   493.442  2672.645   \n",
       "                  beta_[nodegree]  -454.568  492.429 -1360.717   461.760   \n",
       "                  beta_[married]   3926.351  519.744  2930.813  4873.111   \n",
       "                  alpha_outcome    4320.328  368.753  3628.037  4996.010   \n",
       "                  sigma            6568.130  149.699  6293.193  6860.301   \n",
       "\n",
       "                                   r_hat  \n",
       "1-stage-model     alpha_trt          1.0  \n",
       "                  beta_[treat]       1.0  \n",
       "                  beta_[nodegree]    1.0  \n",
       "                  beta_[married]     1.0  \n",
       "                  beta_ps            1.0  \n",
       "                  alpha_outcome      1.0  \n",
       "                  sigma              1.0  \n",
       "2-stage-model     beta_[treat]       1.0  \n",
       "                  beta_[nodegree]    1.0  \n",
       "                  beta_[married]     1.0  \n",
       "                  beta_ps            1.0  \n",
       "                  alpha_outcome      1.0  \n",
       "                  sigma              1.0  \n",
       "Simple Regression beta_[treat]       1.0  \n",
       "                  beta_[nodegree]    1.0  \n",
       "                  beta_[married]     1.0  \n",
       "                  alpha_outcome      1.0  \n",
       "                  sigma              1.0  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_estimate = pd.concat(\n",
    "    {\n",
    "        \"1-stage-model\": az.summary(\n",
    "            idata_lalonde,\n",
    "            var_names=[\"alpha_trt\", \"beta_\", \"beta_ps\", \"alpha_outcome\", \"sigma\"],\n",
    "        ),\n",
    "        \"2-stage-model\": az.summary(\n",
    "            idata_outcome_2s_lalonde,\n",
    "            var_names=[\"beta_\", \"beta_ps\", \"alpha_outcome\", \"sigma\"],\n",
    "        ),\n",
    "        \"Simple Regression\": az.summary(\n",
    "            idata_outcome_simple_reg_lalonde,\n",
    "            var_names=[\"beta_\", \"alpha_outcome\", \"sigma\"],\n",
    "        ),\n",
    "    }\n",
    ")\n",
    "compare_estimate[[\"mean\", \"sd\", \"hdi_3%\", \"hdi_97%\", \"r_hat\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The model estimates are basically identical. We should expect mirrored propensity score distributions indicating that feedback wasn't an issue. The outcome model leaned primarily on the covariate profile $X$ to derive the treatment effect estimate. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "compare_propensity_dists(idata_treatment_2s_lalonde, idata_lalonde)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Both estimates of the treatment effects accord well with values in the literature. We can be happy that both models are picking up on the treatment effects reasonably well, despite having a minimalist outcome  model. This is because in the Bayesian setting the conditional distribution of $X, T$ are generally sufficient when there is no unmeasured confounders. Here the model somewhat ignores the propensity score coefficients `beta_ps`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### NHEFS \n",
    "\n",
    "Finally we turn to the NHEFS data as discussed by Hernan in {cite:p}`Hernan2024-HERCIW`. This data is known to be have a complex covariate profile for measuring aspects smokers health. We might suspect that there is some unmeasured confounding in this data set that would be hard to pick up on with simple regression controls. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
ageracetrtsmokeintensitysmokeyrsoutcome
042103029-10.093960
1360020242.604970
2561020269.414486
368103534.990117
4400020194.989251
\n",
       "
"
      ],
      "text/plain": [
       "   age  race  trt  smokeintensity  smokeyrs    outcome\n",
       "0   42     1    0              30        29 -10.093960\n",
       "1   36     0    0              20        24   2.604970\n",
       "2   56     1    0              20        26   9.414486\n",
       "3   68     1    0               3        53   4.990117\n",
       "4   40     0    0              20        19   4.989251"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = cp.load_data(\"nhefs\")\n",
    "df[[\"age\", \"race\", \"trt\", \"smokeintensity\", \"smokeyrs\", \"outcome\"]].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "tags": [
     "hide-output"
    ]
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_trt_std, beta_std, beta_ps, alpha_trt, alpha_outcome, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3fc469410746442c8563b91bac34d174",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 56 seconds.\n",
      "Sampling: [alpha_trt, beta_trt_std, t_pred]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_trt_std, alpha_trt]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "cf458ef84a9c4f789969455961520ee7",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 40 seconds.\n",
      "Sampling: [alpha_outcome, beta_ps, beta_ps_spline, beta_std, like, sigma]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, beta_ps, alpha_outcome, beta_ps_spline, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4ac5c095af1c4b91b4f7647195e0bac1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 29 seconds.\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, alpha_outcome, sigma]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "dad8c22d444345e2b4e6b916e6d44ea2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/pymc/step_methods/hmc/quadpotential.py:316: RuntimeWarning: overflow encountered in dot\n",
      "  return 0.5 * np.dot(x, v_out)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling 4 chains for 2_000 tune and 2_000 draw iterations (8_000 + 8_000 draws total) took 13 seconds.\n"
     ]
    }
   ],
   "source": [
    "coords = {\n",
    "    \"betas\": [\"trt\", \"age\", \"race\", \"sex\", \"smokeintensity\", \"smokeyrs\", \"wt71\"],\n",
    "    \"betas_trt\": [\n",
    "        \"age\",\n",
    "        \"race\",\n",
    "        \"sex\",\n",
    "        \"smokeintensity\",\n",
    "        \"smokeyrs\",\n",
    "        \"wt71\",\n",
    "        \"active_1\",\n",
    "        \"active_2\",\n",
    "        \"education_2\",\n",
    "        \"education_3\",\n",
    "        \"education_4\",\n",
    "        \"education_5\",\n",
    "        \"exercise_1\",\n",
    "        \"exercise_2\",\n",
    "        \"age^2\",\n",
    "        \"wt71^2\",\n",
    "        \"smokeintensity^2\",\n",
    "        \"smokeyrs^2\",\n",
    "    ],\n",
    "    \"obs\": range(df.shape[0]),\n",
    "}\n",
    "\n",
    "N = df.shape[0]\n",
    "X_trt = df[\n",
    "    [\n",
    "        \"age\",\n",
    "        \"race\",\n",
    "        \"sex\",\n",
    "        \"smokeintensity\",\n",
    "        \"smokeyrs\",\n",
    "        \"wt71\",\n",
    "        \"active_1\",\n",
    "        \"active_2\",\n",
    "        \"education_2\",\n",
    "        \"education_3\",\n",
    "        \"education_4\",\n",
    "        \"education_5\",\n",
    "        \"exercise_1\",\n",
    "        \"exercise_2\",\n",
    "        \"age^2\",\n",
    "        \"wt71^2\",\n",
    "        \"smokeintensity^2\",\n",
    "        \"smokeyrs^2\",\n",
    "    ]\n",
    "]\n",
    "X_trt = (X_trt - X_trt.mean(axis=0)) / X_trt.std(axis=0)\n",
    "# Note the significantly reduced outcome model specification.\n",
    "X_outcome = df[[\"trt\", \"age\", \"race\", \"sex\", \"smokeintensity\", \"smokeyrs\", \"wt71\"]]\n",
    "X_outcome = (X_outcome - X_outcome.mean(axis=0)) / X_outcome.std(axis=0)\n",
    "T_data = df[\"trt\"].values\n",
    "X_outcome[\"trt\"] = T_data\n",
    "Y_data = df[\"outcome\"].values\n",
    "\n",
    "priors = {\n",
    "    \"beta_\": [0, 3],\n",
    "    \"beta_trt\": [0, 1],\n",
    "    \"alpha_trt\": [0, 1],\n",
    "    \"alpha_outcome\": [0, 5],\n",
    "    \"sigma\": 10,\n",
    "    \"beta_ps\": [0, 10],\n",
    "}\n",
    "\n",
    "nhefs_model = make_joint_model(X_trt, X_outcome, T_data, Y_data, coords, priors)\n",
    "with nhefs_model:\n",
    "    idata_nhefs = pm.sample(**sampler_kwargs)\n",
    "\n",
    "\n",
    "(\n",
    "    idata_treatment_2s_nhefs,\n",
    "    idata_outcome_2s_nhefs,\n",
    "    treatment_model_nhefs,\n",
    "    outcome_model_nhefs,\n",
    ") = make_2step_model(\n",
    "    X_trt,\n",
    "    X_outcome,\n",
    "    T_data,\n",
    "    Y_data,\n",
    "    coords,\n",
    "    priors=priors,\n",
    "    spline_component=True,\n",
    ")\n",
    "\n",
    "\n",
    "reg_model_nhefs, idata_outcome_simple_reg_nhefs = make_reg_model(\n",
    "    X_outcome, Y_data, coords, priors=priors\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = az.plot_forest(\n",
    "    [idata_outcome_2s_nhefs, idata_nhefs, idata_outcome_simple_reg_nhefs],\n",
    "    var_names=[\"beta_\"],\n",
    "    model_names=[\"2 Stage\", \"1 Stage\", \"Simple Regression\"],\n",
    "    combined=True,\n",
    "    figsize=(10, 4),\n",
    ")\n",
    "\n",
    "ax[0].axvline(3.4, label=\"True Treatment Value\", color=\"k\")\n",
    "ax[0].set_title(\"Comparing Joint and 2 Stage Propensity Score Parameter Fits\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here we see the model specifications start to come apart slightly, although the effect of feedback seems to primarily influence the impact of age on the outcome rather than the treatment estimate. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
meansdhdi_3%hdi_97%r_hat
1-stage-modelalpha_trt-1.1460.061-1.262-1.0341.0
beta_[trt]3.4870.4452.6374.3101.0
beta_[age]-1.0180.620-2.1870.1281.0
beta_[race]-0.3230.273-0.8220.1951.0
beta_[sex]-1.1450.295-1.706-0.5991.0
beta_[smokeintensity]-0.4310.319-1.0240.1751.0
beta_[smokeyrs]-0.3030.540-1.3180.7021.0
beta_[wt71]-1.2210.281-1.742-0.6981.0
alpha_outcome5.2041.0023.2237.0041.0
beta_ps-13.4763.820-20.775-6.4201.0
2-stage-modelbeta_[trt]3.3190.4352.5174.1551.0
beta_[age]-1.9370.469-2.824-1.0681.0
beta_[race]-0.1010.257-0.5750.3921.0
beta_[sex]-0.9400.255-1.409-0.4541.0
beta_[smokeintensity]-0.0520.255-0.5420.4201.0
beta_[smokeyrs]0.3170.424-0.5101.0941.0
beta_[wt71]-1.3930.222-1.818-0.9801.0
alpha_outcome1.3632.904-4.2566.5571.0
beta_ps-0.02310.048-18.15419.1921.0
Simple Regressionbeta_[trt]3.2700.4352.4504.0871.0
beta_[age]-2.4270.387-3.142-1.6881.0
beta_[race]0.2040.193-0.1410.5771.0
beta_[sex]-0.6850.218-1.096-0.2781.0
beta_[smokeintensity]0.2700.199-0.0880.6661.0
beta_[smokeyrs]0.5470.393-0.2031.2861.0
beta_[wt71]-1.5430.208-1.932-1.1511.0
alpha_outcome1.7950.2161.3712.1841.0
\n",
       "
"
      ],
      "text/plain": [
       "                                           mean      sd  hdi_3%  hdi_97%  \\\n",
       "1-stage-model     alpha_trt              -1.146   0.061  -1.262   -1.034   \n",
       "                  beta_[trt]              3.487   0.445   2.637    4.310   \n",
       "                  beta_[age]             -1.018   0.620  -2.187    0.128   \n",
       "                  beta_[race]            -0.323   0.273  -0.822    0.195   \n",
       "                  beta_[sex]             -1.145   0.295  -1.706   -0.599   \n",
       "                  beta_[smokeintensity]  -0.431   0.319  -1.024    0.175   \n",
       "                  beta_[smokeyrs]        -0.303   0.540  -1.318    0.702   \n",
       "                  beta_[wt71]            -1.221   0.281  -1.742   -0.698   \n",
       "                  alpha_outcome           5.204   1.002   3.223    7.004   \n",
       "                  beta_ps               -13.476   3.820 -20.775   -6.420   \n",
       "2-stage-model     beta_[trt]              3.319   0.435   2.517    4.155   \n",
       "                  beta_[age]             -1.937   0.469  -2.824   -1.068   \n",
       "                  beta_[race]            -0.101   0.257  -0.575    0.392   \n",
       "                  beta_[sex]             -0.940   0.255  -1.409   -0.454   \n",
       "                  beta_[smokeintensity]  -0.052   0.255  -0.542    0.420   \n",
       "                  beta_[smokeyrs]         0.317   0.424  -0.510    1.094   \n",
       "                  beta_[wt71]            -1.393   0.222  -1.818   -0.980   \n",
       "                  alpha_outcome           1.363   2.904  -4.256    6.557   \n",
       "                  beta_ps                -0.023  10.048 -18.154   19.192   \n",
       "Simple Regression beta_[trt]              3.270   0.435   2.450    4.087   \n",
       "                  beta_[age]             -2.427   0.387  -3.142   -1.688   \n",
       "                  beta_[race]             0.204   0.193  -0.141    0.577   \n",
       "                  beta_[sex]             -0.685   0.218  -1.096   -0.278   \n",
       "                  beta_[smokeintensity]   0.270   0.199  -0.088    0.666   \n",
       "                  beta_[smokeyrs]         0.547   0.393  -0.203    1.286   \n",
       "                  beta_[wt71]            -1.543   0.208  -1.932   -1.151   \n",
       "                  alpha_outcome           1.795   0.216   1.371    2.184   \n",
       "\n",
       "                                         r_hat  \n",
       "1-stage-model     alpha_trt                1.0  \n",
       "                  beta_[trt]               1.0  \n",
       "                  beta_[age]               1.0  \n",
       "                  beta_[race]              1.0  \n",
       "                  beta_[sex]               1.0  \n",
       "                  beta_[smokeintensity]    1.0  \n",
       "                  beta_[smokeyrs]          1.0  \n",
       "                  beta_[wt71]              1.0  \n",
       "                  alpha_outcome            1.0  \n",
       "                  beta_ps                  1.0  \n",
       "2-stage-model     beta_[trt]               1.0  \n",
       "                  beta_[age]               1.0  \n",
       "                  beta_[race]              1.0  \n",
       "                  beta_[sex]               1.0  \n",
       "                  beta_[smokeintensity]    1.0  \n",
       "                  beta_[smokeyrs]          1.0  \n",
       "                  beta_[wt71]              1.0  \n",
       "                  alpha_outcome            1.0  \n",
       "                  beta_ps                  1.0  \n",
       "Simple Regression beta_[trt]               1.0  \n",
       "                  beta_[age]               1.0  \n",
       "                  beta_[race]              1.0  \n",
       "                  beta_[sex]               1.0  \n",
       "                  beta_[smokeintensity]    1.0  \n",
       "                  beta_[smokeyrs]          1.0  \n",
       "                  beta_[wt71]              1.0  \n",
       "                  alpha_outcome            1.0  "
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_estimate = pd.concat(\n",
    "    {\n",
    "        \"1-stage-model\": az.summary(\n",
    "            idata_nhefs, var_names=[\"alpha_trt\", \"beta_\", \"alpha_outcome\", \"beta_ps\"]\n",
    "        ),\n",
    "        \"2-stage-model\": az.summary(\n",
    "            idata_outcome_2s_nhefs, var_names=[\"beta_\", \"alpha_outcome\", \"beta_ps\"]\n",
    "        ),\n",
    "        \"Simple Regression\": az.summary(\n",
    "            idata_outcome_simple_reg_nhefs, var_names=[\"beta_\", \"alpha_outcome\"]\n",
    "        ),\n",
    "    }\n",
    ")\n",
    "compare_estimate[[\"mean\", \"sd\", \"hdi_3%\", \"hdi_97%\", \"r_hat\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "compare_propensity_dists(idata_treatment_2s_nhefs, idata_nhefs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Two-Stage Outcome Modelling with CausalPy\n",
    "\n",
    "Next we show how to achieve these steps with the simpler CausalPy experiment API. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "tags": [
     "hide-output"
    ]
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std]\n",
      "Sampling 4 chains for 2_000 tune and 10_000 draw iterations (8_000 + 40_000 draws total) took 26 seconds.\n",
      "Sampling: [beta_std, t_pred]\n",
      "Sampling: [t_pred]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       ""
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "formula = \"\"\"trt ~ 1 + age + race + sex + smokeintensity + smokeyrs + wt71 + active_1 + active_2 + \n",
    "         education_2 + education_3 + education_4 + education_5 + exercise_1 + exercise_2\"\"\"\n",
    "\n",
    "df_standardised = (df - df.mean(axis=0)) / df.std(axis=0)\n",
    "df_standardised[\"trt\"] = df[\"trt\"]\n",
    "df_standardised[\"outcome\"] = df[\"outcome\"]\n",
    "result = cp.InversePropensityWeighting(\n",
    "    df_standardised,\n",
    "    formula=formula,\n",
    "    outcome_variable=\"outcome\",\n",
    "    weighting_scheme=\"robust\",  ## Will be used by plots after estimation if no other scheme is specified.\n",
    "    model=cp.pymc_models.PropensityScore(\n",
    "        sample_kwargs={\n",
    "            \"chains\": 4,\n",
    "            \"tune\": 2000,\n",
    "            \"draws\": 10000,\n",
    "            \"target_accept\": 0.95,\n",
    "            \"random_seed\": 18,\n",
    "            \"progressbar\": False,\n",
    "            \"mp_ctx\": \"spawn\",\n",
    "        },\n",
    "    ),\n",
    ")\n",
    "\n",
    "result"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Comparing Inverse Propensity Score Weighting and Covariate Adjustment\n",
    "\n",
    "The two step procedure doesn't jusst apply for regression adjustment methods as we've seen here, but can be used to apply inverse weighting techniques too. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/IPython/core/events.py:82: UserWarning: Creating legend with loc=\"best\" can be slow with large amounts of data.\n",
      "  func(*args, **kwargs)\n",
      "/Users/nathanielforde/mambaforge/envs/CausalPy/lib/python3.13/site-packages/IPython/core/pylabtools.py:170: UserWarning: Creating legend with loc=\"best\" can be slow with large amounts of data.\n",
      "  fig.canvas.print_figure(bytes_io, **kw)\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_ate(result.idata);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "which can be compared against the two-step regression adjustment here. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "tags": [
     "hide-output"
    ]
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Sampling: [beta_ps, beta_std, like, sigma]\n",
      "Initializing NUTS using jitter+adapt_diag...\n",
      "Multiprocess sampling (4 chains in 4 jobs)\n",
      "NUTS: [beta_std, beta_ps, sigma]\n",
      "Sampling 4 chains for 2_000 tune and 10_000 draw iterations (8_000 + 40_000 draws total) took 47 seconds.\n"
     ]
    }
   ],
   "source": [
    "idata_outcome_cp, model_outcome_cp = result.model.fit_outcome_model(\n",
    "    result.X_outcome,\n",
    "    result.y,\n",
    "    result.coords,\n",
    "    priors={\"b_outcome\": [0, 3], \"sigma\": 10, \"beta_ps\": [0, 10]},\n",
    "    noncentred=True,\n",
    "    normal_outcome=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Yielding similar, but not identical results. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
meansdhdi_3%hdi_97%mcse_meanmcse_sdess_bulkess_tailr_hat
beta_[Intercept]2.0931.344-0.4344.6120.0140.0099380.014843.01.0
beta_[age]-2.2100.721-3.543-0.8350.0070.00410668.017142.01.0
beta_[race]0.1510.312-0.4450.7270.0030.00212175.020768.01.0
beta_[sex]-0.7970.409-1.562-0.0240.0040.00211010.017907.01.0
beta_[smokeintensity]0.1780.337-0.4690.7970.0030.00212015.019490.01.0
beta_[smokeyrs]0.4670.602-0.6821.5750.0060.00311849.019291.01.0
beta_[wt71]-1.5090.214-1.920-1.1120.0010.00133903.028828.01.0
beta_[active_1]-0.5390.214-0.930-0.1220.0010.00129101.029625.01.0
beta_[active_2]-0.1160.207-0.5120.2660.0010.00131383.029074.01.0
beta_[education_2]0.4160.253-0.0710.8810.0020.00125487.028436.01.0
beta_[education_3]0.3980.275-0.1370.9040.0020.00123112.026560.01.0
beta_[education_4]0.3600.249-0.1170.8210.0020.00120161.026766.01.0
beta_[education_5]0.0300.302-0.5140.6240.0020.00115996.023783.01.0
beta_[exercise_1]0.2090.279-0.3170.7370.0020.00120495.026199.01.0
beta_[exercise_2]0.2720.332-0.3360.9130.0030.00214760.021435.01.0
beta_[trt]3.3180.4342.4764.1050.0020.00240864.030723.01.0
\n",
       "
"
      ],
      "text/plain": [
       "                        mean     sd  hdi_3%  hdi_97%  mcse_mean  mcse_sd  \\\n",
       "beta_[Intercept]       2.093  1.344  -0.434    4.612      0.014    0.009   \n",
       "beta_[age]            -2.210  0.721  -3.543   -0.835      0.007    0.004   \n",
       "beta_[race]            0.151  0.312  -0.445    0.727      0.003    0.002   \n",
       "beta_[sex]            -0.797  0.409  -1.562   -0.024      0.004    0.002   \n",
       "beta_[smokeintensity]  0.178  0.337  -0.469    0.797      0.003    0.002   \n",
       "beta_[smokeyrs]        0.467  0.602  -0.682    1.575      0.006    0.003   \n",
       "beta_[wt71]           -1.509  0.214  -1.920   -1.112      0.001    0.001   \n",
       "beta_[active_1]       -0.539  0.214  -0.930   -0.122      0.001    0.001   \n",
       "beta_[active_2]       -0.116  0.207  -0.512    0.266      0.001    0.001   \n",
       "beta_[education_2]     0.416  0.253  -0.071    0.881      0.002    0.001   \n",
       "beta_[education_3]     0.398  0.275  -0.137    0.904      0.002    0.001   \n",
       "beta_[education_4]     0.360  0.249  -0.117    0.821      0.002    0.001   \n",
       "beta_[education_5]     0.030  0.302  -0.514    0.624      0.002    0.001   \n",
       "beta_[exercise_1]      0.209  0.279  -0.317    0.737      0.002    0.001   \n",
       "beta_[exercise_2]      0.272  0.332  -0.336    0.913      0.003    0.002   \n",
       "beta_[trt]             3.318  0.434   2.476    4.105      0.002    0.002   \n",
       "\n",
       "                       ess_bulk  ess_tail  r_hat  \n",
       "beta_[Intercept]         9380.0   14843.0    1.0  \n",
       "beta_[age]              10668.0   17142.0    1.0  \n",
       "beta_[race]             12175.0   20768.0    1.0  \n",
       "beta_[sex]              11010.0   17907.0    1.0  \n",
       "beta_[smokeintensity]   12015.0   19490.0    1.0  \n",
       "beta_[smokeyrs]         11849.0   19291.0    1.0  \n",
       "beta_[wt71]             33903.0   28828.0    1.0  \n",
       "beta_[active_1]         29101.0   29625.0    1.0  \n",
       "beta_[active_2]         31383.0   29074.0    1.0  \n",
       "beta_[education_2]      25487.0   28436.0    1.0  \n",
       "beta_[education_3]      23112.0   26560.0    1.0  \n",
       "beta_[education_4]      20161.0   26766.0    1.0  \n",
       "beta_[education_5]      15996.0   23783.0    1.0  \n",
       "beta_[exercise_1]       20495.0   26199.0    1.0  \n",
       "beta_[exercise_2]       14760.0   21435.0    1.0  \n",
       "beta_[trt]              40864.0   30723.0    1.0  "
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "az.summary(idata_outcome_cp, var_names=[\"beta_\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = az.plot_posterior(\n",
    "    idata_outcome_cp,\n",
    "    var_names=[\"beta_\"],\n",
    "    coords={\"outcome_coeffs\": [\"trt\"]},\n",
    "    figsize=(10, 5),\n",
    "    ref_val=3.5,\n",
    ")\n",
    "ax.set_title(\n",
    "    \"Treatment Effect Estimated using 2-stage \\n Regression Adjustment Approach with reduced covariates\"\n",
    ");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Conclusion: Modularity as Causal Discipline\n",
    "\n",
    "When attempting to estimate treatment effects using Bayesian inference, a natural but risky strategy is to fit a joint model for both the treatment assignment and the outcome. That is, to specify a full model and infer the parameters of both components simultaneously.\n",
    "\n",
    "However, this joint approach introduces a feedback loop: the outcome $Y$ can influence the estimation of the treatment mechanism $P(T | X)$. This violates the original logic of design-based inference, where treatment assignment should be modeled independently of the observed outcomes. This phenomenon is often subtle but can lead to biased treatment effect estimates.\n",
    "\n",
    "Across several examples, we have shown that fitting a full joint model distorts the treatment effect estimate relative to a two-step (modular) approach.\n",
    "In other cases, joint and modular approaches yield nearly identical estimates — usually when the outcome is well-identified from covariates alone. With these observations in scope, we recommend that practitioners generally follow a two-step or modular approach. Either two-stage inverse propensity score weighting or regression adjustment with the propensity score as an additional covariate. Both methods are available now in `CausalPy`. \n",
    "\n",
    "Framed this way we can see that joint model violates the temporal precedence of the treatment assignment and outcome process. The 2-stage Bayesian procedures ensure that the causal ordering encoded in the actual data generating process is respected in the estimation process. The confounding adjustment achieved with propensity score must occur without access to information about the outcome. A well-specified propensity score model can substantially improve causal estimates (as we've seen), especially when the outcome model is weak or mis-specified. This allows for a form of __doubly-robust inference__ as discussed in {cite:p}`aronowFoundations` and {cite:p}`liBayesianProp`. Propensity scores do not only serve to reduce dimensionality; they formalize the treatment mechanism and encode information that the outcome model might fail to recover. This explains their continued prominence in modern causal inference and usefulness in the Bayesian setting.\n",
    "\n",
    "### References\n",
    ":::{bibliography}\n",
    ":filter: docname in docnames\n",
    ":::"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Watermark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Last updated: Tue Jul 29 2025\n",
      "\n",
      "Python implementation: CPython\n",
      "Python version       : 3.13.5\n",
      "IPython version      : 9.4.0\n",
      "\n",
      "pytensor: 2.31.7\n",
      "xarray  : 2025.7.0\n",
      "\n",
      "matplotlib: 3.10.3\n",
      "arviz     : 0.21.0\n",
      "pandas    : 2.3.1\n",
      "causalpy  : 0.4.2\n",
      "patsy     : 1.0.1\n",
      "pymc      : 5.23.0\n",
      "numpy     : 2.3.1\n",
      "\n",
      "Watermark: 2.5.0\n",
      "\n"
     ]
    }
   ],
   "source": [
    "%load_ext watermark\n",
    "%watermark -n -u -v -iv -w -p pytensor,xarray"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "CausalPy",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}