Estimating the Effect of Cluster-Level Adherence on an Individual Binary Outcome with a Complex Sampling Design

• Activity Number: 190
• Type: Contributed
• Date/Time: Monday, August 1, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Zhulin He*+ and Babette Brumback and Richard Rheingans and Matthew Freeman and Leslie Greene and Leslie Greene and Leslie Greene
• Companies: University of Florida and University of Florida and University of Florida and Emory University and Emory University and Emory University and Emory University
• Keywords: structural nested models ; complex sampling design ; instrumental variables ; estimating equations ; unmeasured confounding ; global health

Abstract

We wish to estimate the effect of school-level adherence on individual absenteeism in the context of a school-based water, sanitation, and hygiene intervention in Western Kenya. Schools within strata were disproportionately sampled and randomized to one of three interventions. Next, students within schools were disproportionately sampled and measured for outcomes such as absenteeism. We use double inverse-probability weighting to adjust for the disproportionate sampling and the association of individual-level confounders with randomization. We develop and apply methods based on structural nested models to estimate effects of adherence assessed in terms of relative risks, using school-level randomization as an instrumental variable and using the double weights to adjust for complex sampling and individual-level confounding.