Daifeng Han and Richard Valliant Publish on How Models Affect Calibration Estimators
Daifeng Han, Ph.D., and Richard Valliant, Ph.D., have coauthored a new article in Journal of Survey Statistics and Methodology: Effects of Outcome and Response Models on Single-Step Calibration Estimators.
Dr. Han is a Westat senior statistician, and Dr. Valliant is a Research Professor Emeritus at the Institute for Social Research, University of Michigan and University of Maryland, and a Westat Nonresident Senior Statistical Fellow.
The article furthers the understanding of commonly used calibration estimators, post-stratification, raking, and generalized regression estimator (GREG) when nonresponse is present in sample surveys.
The authors review the literature of calibration estimators, present their design-based analytic results in the presence of nonresponse, and include a simulation study demonstrating how the outcome and response models affect the performance of the estimators.