Simultaneous Sensitivity Analysis for Observational Studies Using Full Matching with Multiple Controls

• Activity Number: 337
• Type: Topic Contributed
• Date/Time: Tuesday, August 3, 2010 : 10:30 AM to 12:20 PM
• Sponsor: ENAR
• Author(s): Dylan Small*+ and Joseph L. Gastwirth and Abba Krieger and Paul Rosenbaum
• Companies: University of Pennsylvania and Washington University and University of Pennsylvania and University of Pennsylvania
• Keywords: observational study ; sensitivity analysis ; matching

Abstract

In a matched observational study, a sensitivity analysis asks how the conclusions of the study would change if the matching had failed to adjust for an unobserved covariate with particular attributes. A ?simultaneous ?sensitivity analysis characterizes the unobserved covariate u in terms of two sensitivity parameters which relate u to treatment and to response. Previous work developed a simultaneous sensitivity analysis for matched pairs. Our current work extends this to matching with multiple controls and to full matching, using the technique of asymptotic separability. An example concerns the possibility that the military caused an increase in smoking by soldiers by various programs that subsidized cigarettes.