The Causal Cookbook: Recipes for Propensity Scores, G-Computation, and Doubly Robust Standardization

Abstract

Recent developments in the causal-inference literature have renewed psychologists’ interest in how to improve causal conclusions based on observational data. A lot of the recent writing has focused on concerns of causal identification (under which conditions is it, in principle, possible to recover causal effects?); in this primer, we turn to causal estimation (how do researchers actually turn the data into an effect estimate?) and modern approaches to it that are commonly used in epidemiology. First, we explain how causal estimands can be defined rigorously with the help of the potential-outcomes framework, and we highlight four crucial assumptions necessary for causal inference to succeed (exchangeability, positivity, consistency, and noninterference). Next, we present three types of approaches to causal estimation and compare their strengths and weaknesses: propensity-score methods (in which the independent variable is modeled as a function of controls), g-computation methods (in which the dependent variable is modeled as a function of both controls and the independent variable), and doubly robust estimators (which combine models for both independent and dependent variables). A companion R Notebook is available at github.com/ArthurChatton/CausalCookbook. We hope that this nontechnical introduction not only helps psychologists and other social scientists expand their causal toolbox but also facilitates communication across disciplinary boundaries when it comes to causal inference, a research goal common to all fields of research.

Designing target trials using electronic health records: A case study of second-line disease-modifying anti-rheumatic drugs and cardiovascular disease outcomes in patients with rheumatoid arthritis

“…Researchers may opt to use data-driven approaches for covariate selection (e.g., lasso) but it can add to the computational time and complexity. Covariates can be used in both weighting (steps 1 and 2) and outcome models (step 3) as it may safeguard against residual imbalance [40]. All weights should be stabilized (and possibly truncated) to prevent large weights on rare individuals.…”

Establishing causal inferences from experimental and observational data: A critical review and primer for sport and exercise psychology

“…The final step involves using statistical methods to estimate the causal effect from the observed data. Depending on the empirical estimand derived from the identification step, various estimation techniques can be employed (see Chatton & Rohrer, 2024;Mulder et al, 2024;Quintana, 2024 for recent examples). The goal is to obtain a quantitative measure of the causal effect, taking into account the assumptions and the identified relationships.…”

“…The focus of the remainder of this article will be on the first two steps of this process because they are the most overlooked by those unfamiliar with causal inference, while simultaneously being the most essential components of the causal inference process. Specifically, if researchers are unclear or ambiguous about what causal effect they are interested in, or what assumptions need to be made in order to identify their causal effect, no sophisticated estimation algorithm or statistical analysis can render their causal inference salvageable (Chatton & Rohrer, 2024;Lundberg et al, 2021). The procedures and implications associated with these first two steps are further explained below.…”