"Quantifying and Correcting Generalization Bias"
Eloise Kaizar, Ph.D., The Ohio State University
February 9, 2010 @ CANCELLED
Biostatistics
TITLE: Quantifying and Correcting Generalization Bias
Randomized controlled trials (RCTs) are the traditional gold standard evidence for medical decision-making. However, protocols that limit enrollment eligibility introduce selection error that severely limits a RCT's applicability to a wide range of patients. Conversely, high quality observational data can be representative of entire populations, but freedom to choose treatment can bias estimators based on this data. Observational methods may be useful in quantifying the size of possible bias due to recruitment protocols. Further, we propose and assess a simple estimator of effect size that capitalizes on the RCT's strong internal validity and the observational study's strong external validity. We evaluate its properties within a formal framework of causal estimation and compare our estimator to more traditional estimators based on single sources of evidence. We show that under some reasonable data assumptions our estimator has smaller bias and better coverage than commonly used estimates based on randomized or observational studies alone.
