In an increasingly common class of studies, the goal is to evaluate
causal effects of treatments that are only partially controlled by the
investigator. In such studies there are two conflicting features: (1) a
model on the full cohort design and data can identify the causal
effects of interest, but can be sensitive to extreme regions of that
design's data, where model specification can have more impact; and (2)
models on a reduced design (i.e., a subset of the full data), for
example, conditional likelihood on matched subsets of data, can avoid
such sensitivity, but do not generally identify the causal effects. We
propose a general framework, ``polydesign'', that can both identify
causal effects and also is robust to model specification by exploring
combinations of both the full and reduced designs. We discuss
implementation of polydesign methods, and provide an illustration in
the evaluation of a Needle Exchange Program. We further discuss
strategies of designing location-cotrolled follow-up studies, in order
to achieve larger treatment benefit and to increase the accurary of
evaluation. This is a joint work with Constantine Frangakis.
Meet the speaker in Room 212 Cockins Hall at 4:30
p.m. Refreshments will be served.