Answers are grounded in this paper and cite their sources.
Simulation study demonstrates substantial bias from significance testing in variable selection, indicating change-in-estimate criteria provide superior effect estimation.
Journal Article THE IMPACT OF CONFOUNDER SELECTION CRITERIA ON EFFECT ESTIMATION Get access RUTH M. MICKEY, RUTH M. MICKEY 1Department of Mathematics and Statistics, University of VermontBurlington, VT 05405 Reprint requests to Dr. Ruth M. Mickey. Search for other works by this author on: Oxford Academic PubMed Google Scholar SANDER GREENLAND SANDER GREENLAND 2Department of Epidemiology, School of Public Health, University of CaliforniaLos Angeles, CA 90024 Search for other works by this author on: Oxford Academic PubMed Google Scholar American Journal of Epidemiology, Volume 129, Issue 1, January 1989, Pages 125–137, https://doi.org/10.1093/oxfordjournals.aje.a115101 Published: 01 January 1989 Article history Received: 05 July 1988 Published: 01 January 1989
No takes yet. Share an insight, caveat, or question.
MICKEY et al. (1989) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: