Struggles with Survey Weighting and Regression Modeling

Abstract

The general principles of Bayesian data analysis imply that models for survey responses should be constructed conditional on all variables that affect the probability of inclusion and nonresponse, which are also the variables used in survey weighting and clustering. However, such models can quickly become very complicated, with potentially thousands of poststratification cells. It is then a challenge to develop general families of multilevel probability models that yield reasonable Bayesian inferences. We discuss in the context of several ongoing public health and social surveys. This work is currently open-ended, and we conclude with thoughts on how research could proceed to solve these problems.

This paper commented in: [arXiv:0710.5009], [arXiv:0710.5012], [arXiv:0710.5013], [arXiv:0710.5015], [arXiv:0710.5016]. Rejoinder in [arXiv:0710.5019]. Published in at http://dx.doi.org/10.1214/088342306000000691 the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (16)

• High-resolution population estimation using household survey data and building footprints
• Space-time smoothing of complex survey data: Small area estimation for child mortality
• Bayesian Nonparametric Weighted Sampling Inference
• On Identifying and Mitigating Bias in the Estimation of the COVID-19 Case Fatality Rate
• Bayesian hierarchical weighting adjustment and survey inference
• Impact of Frequentist and Bayesian Methods on Survey Sampling Practice: A Selective Appraisal
• Bayesian Inference under Cluster Sampling with Probability Proportional to Size
• Selection-Bias-Corrected Visualization via Dynamic Reweighting
• Semiparametric Bayesian Density Estimation with Disparate Data Sources: A Meta-Analysis of Global Childhood Undernutrition
• Estimating Seroprevalence of SARS-CoV-2 in Ohio: A Bayesian Multilevel Poststratification Approach with Multiple Diagnostic Tests
• Unit Level Modeling of Survey Data for Small Area Estimation Under Informative Sampling: A Comprehensive Overview with Extensions
• Finite Population Survey Sampling: An Unapologetic Bayesian Perspective
• The role of exchangeability in causal inference
• Discussion of "Estimating the Distribution of Dietary Consumption Patterns"
• Handling Attrition in Longitudinal Studies: The Case for Refreshment Samples
• Discussion of "Calibrated Bayes, for Statistics in General, and Missing Data in Particular" by R. J. A. Little