Sensitivity Analysis for an Observational Study on Marriage Dissolution

• Activity Number: 609
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Social Statistics Section
• Author(s): Bo Lu*+
• Companies: The Ohio State University
• Keywords: Sensitivity analysis ; survival analysis ; propensity score matching ; multiple imputation

Abstract

Unlike randomized experiments, treated and control groups may not be comparable at baseline in observational studies. Though baseline differences due to observed covariates can often be removed by statistical adjustments, there is usually the concern that some important baseline differences were not measured. A sensitivity analysis in an observational study addresses the question what the unmeasured covariate would have to be like to alter the conclusions of the study. Sensitivity analysis methods for two groups have been developed, but not many for multiple groups. Also, the applications with survival outcomes are sparse. In this talk, we propose an imputation-based strategy for conducting sensitivity analysis with multiple treatment groups. It is illustrated with an example of time to marriage dissolution due to cohabitation experience prior to marriage.