Estimating the Population Association with a Secondary Outcome in a Case-Control Study with Follow-Up

• Activity Number: 411
• Type: Contributed
• Date/Time: Tuesday, July 31, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Halvor Sommerfelt and Hans Steinsland and Lize van der Merwe and William Blackwelder and Dilruba Nasrin and Tamer Farag and Yukun Wu*+ and Karen Kotloff and Myron Levine and Håkon Gjessing
• Companies: University of Bergen and University of Bergen and University of Western Cape and University of Maryland School of Medicine and University of Maryland School of Medicine and University of Maryland School of Medicine and University of Maryland School of Medicine and University of Maryland School of Medicine and University of Maryland School of Medicine and Norwegian Institute of Public Health
• Keywords: case-control study ; reconstructed cohort

Abstract

If individuals in a case-control study are subsequently followed up, weighted regression analyses can be used to estimate the association between the exposures initially recorded and events occurring thereafter. Such analyses can be conceptualized as being undertaken on a reconstructed source population from which cases and controls stem. To simulate this population, weights are applied to the case-control observations in order to obtain an approximation to the original population. We illustrate the method by analyzing the association between an exposure recorded during the initial case-control study and a dichotomous outcome that occurs during follow-up. The data are from a case-control study of diarrhea in children under five years of age in developing countries.