Zhou, Xiao-Hua (Andrew)Sheng, Elisa2016-04-062016-04-062016-04-062015-12Sheng_washington_0250E_15461.pdfhttp://hdl.handle.net/1773/35544Thesis (Ph.D.)--University of Washington, 2015-12Subject noncompliance is a common problem in the analysis of randomized controlled trials (RCTs); with cognitive behavioral interventions, the addition of provider noncompliance further complicates making causal inference. As a motivating example, we consider a RCT of a Motivational Interviewing (MI)-based behavioral intervention for treating problem drug use. Treatment receipt depends on compliance of both a therapist (provider) and a patient (subject) where MI is `received' when the therapist adheres to the MI protocol and the patient actively participates in the intervention. However, therapists cannot be forced to follow protocol and patients cannot be forced to cooperate in an intervention. In this dissertation, we define causal estimands of interest based on a principal stratication framework, propose methods for estimating these causal estimands, and apply our proposals to a RCT of MI.application/pdfen-USbehavioral intervention; causal inference; motivational interviewing; randomized controlled trialBiostatisticsStatisticsbiostatisticsThesis