The Importance of Covariate Selection in Controlling for Selection Bias in Observational Studies

The assumption of strongly ignorable treatment assignment is required for eliminating selection bias in observational studies. To meet this assumption, researchers often rely on a strategy of selecting covariates that they think will control for selection bias. Theory indicates that the most importa...

Full description

Saved in:
Bibliographic Details
Published inPsychological methods Vol. 15; no. 3; pp. 250 - 267
Main Authors Steiner, Peter M, Cook, Thomas D, Shadish, William R, Clark, M. H
Format Journal Article
LanguageEnglish
Published United States American Psychological Association 01.09.2010
Subjects
Behavioral Research - methods
Behavioral Research - statistics & numerical data
Bias
Causality
Comparative Analysis
Data Interpretation, Statistical
Effect Size
Epidemiologic Methods
Humans
Mathematics
Mathematics - education
Models, Statistical
Observation
Patient Selection
Probability
Propensity Score
Quasiexperimental Design
Random Allocation
Selection
Selection Bias
Statistical Analysis
Undergraduate Students
United States (South)
Vocabulary
Online AccessGet more information

Cover

More Information
Summary:The assumption of strongly ignorable treatment assignment is required for eliminating selection bias in observational studies. To meet this assumption, researchers often rely on a strategy of selecting covariates that they think will control for selection bias. Theory indicates that the most important covariates are those highly correlated with both the real selection process and the potential outcomes. However, when planning a study, it is rarely possible to identify such covariates with certainty. In this article, we report on an extensive reanalysis of a within-study comparison that contrasts a randomized experiment and a quasi-experiment. Various covariate sets were used to adjust for initial group differences in the quasi-experiment that was characterized by self-selection into treatment. The adjusted effect sizes were then compared with the experimental ones to identify which individual covariates, and which conceptually grouped sets of covariates, were responsible for the high degree of bias reduction achieved in the adjusted quasi-experiment. Such results provide strong clues about preferred strategies for identifying the covariates most likely to reduce bias when planning a study and when the true selection process is not known. (Contains 5 figures, 7 tables, and 2 footnotes.)
ISSN:1082-989X
1939-1463
DOI:10.1037/a0018719