Bayesian estimation under informative sampling

DOI10.1214/16-EJS1153zbMATH Open1397.62117arXiv1507.07050OpenAlexW2963140874MaRDI QIDQ309532FDOQ309532

Daniell Toth, Terrance D. Savitsky

Publication date: 7 September 2016

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: Bayesian analysis is increasingly popular for use in social science and other application areas where the data are observations from an informative sample. An informative sampling design leads to inclusion probabilities that are correlated with the response variable of interest. Model inference performed on the observed sample taken from the population will be biased for the population generative model under informative sampling since the balance of information in the sample data is different from that for the population. Typical approaches to account for an informative sampling design under Bayesian estimation are often difficult to implement because they require re-parameterization of the hypothesized generating model, or focus on design, rather than model-based, inference. We propose to construct a pseudo-posterior distribution that utilizes sampling weights based on the marginal inclusion probabilities to exponentiate the likelihood contribution of each sampled unit, which weights the information in the sample back to the population. Our approach provides a nearly automated estimation procedure applicable to any model specified by the data analyst for the population and retains the population model parameterization and posterior sampling geometry. We construct conditions on known marginal and pairwise inclusion probabilities that define a class of sampling designs where $L_1$ consistency of the pseudo posterior is guaranteed. We demonstrate our method on an application concerning the Bureau of Labor Statistics Job Openings and Labor Turnover Survey.

Full work available at URL: https://arxiv.org/abs/1507.07050

Recommendations

• Approximate Bayesian inference under informative sampling
• scientific article
• Fully Bayesian estimation under informative sampling
• Bayesian estimation under informative sampling with unattenuated dependence
• Bayesian predictive inference under informative sampling and transformation
• Bayesian pairwise estimation under dependent informative sampling
• Scalable Bayes under informative sampling
• Bayesian inference in a sample selection model
• Bayesian statistical inference for sampling a finite population
• Bayesian Inference Under Partial Prior Information

zbMATH Keywords

Markov chain Monte CarloGaussian processsurvey samplingDirichlet processBayesian hierarchical modelslatent models

Mathematics Subject Classification ID

Bayesian inference (62F15) Applications of statistics to economics (62P20) Sampling theory, sample surveys (62D05)

Cites Work

• Convergence rates of posterior distributions for non iid observations
• Convergence rates of posterior distributions.
• Weighted Likelihood for Semiparametric Models and Two‐phase Stratified Samples, with Application to Cox Regression
• Some matrix-variate distribution theory: Notational considerations and a Bayesian application
• Title not available (Why is that?)
• Separable covariance arrays via the Tucker product, with applications to multivariate relational data
• Regression Analysis of Data from Complex Surveys
• Bayesian nonparametric weighted sampling inference
• Nonparametric Bayes modeling with sample survey weights
• To Model or Not To Model? Competing Modes of Inference for Finite Population Sampling
• Probability inequalities for likelihood ratios and convergence rates of sieve MLEs
• Multi-level modelling under informative sampling

Cited In (19)

• Bayesian mixture modeling for multivariate conditional distributions
• A Look into the Problem of Preferential Sampling through the Lens of Survey Statistics
• On the normalized power prior
• Uncertainty Estimation for Pseudo‐Bayesian Inference Under Complex Sampling
• Title not available (Why is that?)
• Bayesian estimation methods for survey data with potential applications to health disparities research
• Bayesian weighted inference from surveys
• Computationally efficient Bayesian unit-level models for non-Gaussian data under informative sampling with application to estimation of health insurance coverage
• Accounting for dependent informative sampling in model-based finite population inference
• An information-theoretic approach to incorporating prior information in binomial sampling
• Complex sampling designs: uniform limit theorems and applications
• Bayesian pairwise estimation under dependent informative sampling
• Bayesian ideas in survey sampling: the legacy of Basu
• Bayesian Inference Based on Stationary Fokker-Planck Sampling
• Title not available (Why is that?)
• Bayesian calibration of blue crab (\textit{callinectes sapidus}) abundance indices based on probability surveys
• Bayesian estimation under informative sampling with unattenuated dependence
• A two-stage Bayesian small area estimation approach for proportions
• Conjugate Bayesian unit-level modelling of count data under informative sampling designs

Uses Software

• growfunctions

This page was built for publication: Bayesian estimation under informative sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q309532)