Methods for Constructing and Assessing Propensity Scores

TLDR

The study aims to model the steps for preparing and conducting propensity score analyses, offering step‑by‑step guidance and Stata code applied to an empirical dataset. The authors provide guidance, Stata code, and empirical examples that walk through variable selection, propensity score balance, covariate balance within blocks, matching and weighting strategies, post‑matching balance, and interpretation of treatment effects, illustrated using data from the PC4C palliative care study. Propensity scores effectively adjust for observed differences between treated and comparison groups, but they must be carefully tested before use to estimate treatment effects.

Abstract

Objectives To model the steps involved in preparing for and carrying out propensity score analyses by providing step‐by‐step guidance and Stata code applied to an empirical dataset. Study Design Guidance, Stata code, and empirical examples are given to illustrate (1) the process of choosing variables to include in the propensity score; (2) balance of propensity score across treatment and comparison groups; (3) balance of covariates across treatment and comparison groups within blocks of the propensity score; (4) choice of matching and weighting strategies; (5) balance of covariates after matching or weighting the sample; and (6) interpretation of treatment effect estimates. Empirical Application We use data from the Palliative Care for Cancer Patients (PC4C) study, a multisite observational study of the effect of inpatient palliative care on patient health outcomes and health services use, to illustrate the development and use of a propensity score. Conclusions Propensity scores are one useful tool for accounting for observed differences between treated and comparison groups. Careful testing of propensity scores is required before using them to estimate treatment effects.