Causal Inference from Observational Studies: Matching

Course details

statistics seminar | level: intermediate | register now
for questions related to this event, contact ugent@flames-statistics.com
affiliation: Ghent University

Abstract

This seminar introduces you to Matching as a pre-processing step for reducing imbalance and model dependency in the data and thus resulting in unbiased estimates of causal treatment effects using observational data. You will be introduced to different matching methods including matching based on Propensity Scores (PS). You will be introduced to strategies for evaluating matching and performing outcome analysis. You will also be provided with an understanding of the strengths and limitations of Matching methods especially matching based on PS and some best practices. Some examples from the literature will be presented with an illustration of the different steps using the R software.

Prerequisites

Background readings

Bob Trenwith: Causality-Inferring Causal Effects from Data

Hernán MA, Robins JM (2020). Causal Inference: What If. Boca Raton: Chapman & Hall/CRC.” R by Joy Shi and Sean McGrath

Gary King and Richard Nielsen. 2019. “Why Propensity Scores Should Not Be Used for Matching.” Political Analysis, 27, 4, Pp. 435-454.

Fee

FREE

Venue

online

Instructor

Emmanuel Abatih