|
Abstract:
|
Researchers are often challenged with making causal inferences based on observational data instead of experimental data. In this workshop, we provide an overview of causal inference methods and demonstrate how to implement these methods in Stata. Causal inferences are often framed in terms of treatment effects---measurements of the difference in an outcome between a treatment and the control. Techniques for estimating treatment effects such as regression adjustment, inverse probability weighting, and propensity-score matching will be discussed. We will also introduce methods for estimating treatment effects when observational data complications such as sample selection (data missing not at random) and unobserved confounding are present. In addition, we will show how to estimate the effect of changing levels of a continuous predictor under these complications. A number of examples demonstrating how to perform causal inference and treatment-effect estimation within Stata will be provided. No prior knowledge of Stata is required, but basic familiarity with regression modeling will prove useful.
|
