Bayesian latent pattern mixture models for handling attrition in panel studies with refreshment samples
From MaRDI portal
Publication:288563
DOI10.1214/15-AOAS876zbMATH Open1454.62056arXiv1509.02124OpenAlexW2963135523MaRDI QIDQ288563FDOQ288563
D. Sunshine Hillygus, Jerome P. Reiter, Yajuan Si
Publication date: 27 May 2016
Published in: The Annals of Applied Statistics (Search for Journal in Brave)
Abstract: Many panel studies collect refreshment samples---new, randomly sampled respondents who complete the questionnaire at the same time as a subsequent wave of the panel. With appropriate modeling, these samples can be leveraged to correct inferences for biases caused by non-ignorable attrition. We present such a model when the panel includes many categorical survey variables. The model relies on a Bayesian latent pattern mixture model, in which an indicator for attrition and the survey variables are modeled jointly via a latent class model. We allow the multinomial probabilities within classes to depend on the attrition indicator, which offers additional flexibility over standard applications of latent class models. We present results of simulation studies that illustrate the benefits of this flexibility. We apply the model to correct attrition bias in an analysis of data from the 2007-2008 Associated Press/Yahoo News election panel study.
Full work available at URL: https://arxiv.org/abs/1509.02124
Recommendations
- A Bayesian semiparametric latent variable model for mixed responses
- Latent Pattern Mixture Models for Informative Intermittent Missing Data in Longitudinal Studies
- Combining Panel Data Sets with Attrition and Refreshment Samples
- A Pattern-Mixture Model for Longitudinal Binary Responses with Nonignorable Nonresponse
- A Random Pattern-Mixture Model for Longitudinal Data With Dropouts
- A Bayesian multinomial probit model for the analysis of panel choice data
- Bayesian latent-class mixed-effect hybrid models for dyadic longitudinal data with non-ignorable dropouts
- A Bayesian Approach for the Analysis of Panel‐Count Data with Dependent Termination
Bayesian inference (62F15) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Sampling theory, sample surveys (62D05) Applications of statistics to social sciences (62P25)
Cites Work
- Title not available (Why is that?)
- Adjusting for Nonignorable Drop-Out Using Semiparametric Nonresponse Models
- Title not available (Why is that?)
- Posterior predictive \(p\)-values
- Informative Drop-Out in Longitudinal Data Analysis
- Nonparametric Bayes Modeling of Multivariate Categorical Data
- Latent Pattern Mixture Models for Informative Intermittent Missing Data in Longitudinal Studies
- Missing Data in Longitudinal Studies
- Pattern-Mixture Models for Multivariate Incomplete Data
- Title not available (Why is that?)
- A weakly informative default prior distribution for logistic and other regression models
- Handling attrition in longitudinal studies: the case for refreshment samples
- Inference in panel data models under attrition caused by unobservables
- Modeling Longitudinal Data with Nonignorable Dropouts Using a Latent Dropout Class Model
- A General Class of Pattern Mixture Models for Nonignorable Dropout with Many Possible Dropout Times
- Pattern-mixture models with proper time dependence
- Combining Panel Data Sets with Attrition and Refreshment Samples
- Gibbs Sampling Methods for Stick-Breaking Priors
- Missing Covariates in Generalized Linear Models When the Missing Data Mechanism is Non-ignorable
- A class of pattern-mixture models for normal incomplete data
- Title not available (Why is that?)
- Alternative statistical models and representations for large sparse multi-dimensional contingency tables
- Bayesian latent pattern mixture models for handling attrition in panel studies with refreshment samples
- On the Bias of the Multiple-Imputation Variance Estimator in Survey Sampling
- Principal Stratification Approach to Broken Randomized Experiments
- Title not available (Why is that?)
- Reparameterizing the Pattern Mixture Model for Sensitivity Analyses Under Informative Dropout
- Multiple Imputation for Model Checking: Completed‐Data Plots with Missing and Latent Data
- Protecting Against Nonrandomly Missing Data in Longitudinal Studies
Cited In (6)
- A panel quantile approach to attrition bias in big data: evidence from a randomized experiment
- Bayesian latent pattern mixture models for handling attrition in panel studies with refreshment samples
- Statistical modeling of longitudinal data with non-ignorable non-monotone missingness with semiparametric Bayesian and machine learning components
- Nonresponse bias analysis in longitudinal studies: a comparative review with an application to the early childhood longitudinal study
- Bayesian profiling multiple imputation for missing hemoglobin values in electronic health records
- Combining Panel Data Sets with Attrition and Refreshment Samples
Uses Software
This page was built for publication: Bayesian latent pattern mixture models for handling attrition in panel studies with refreshment samples
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q288563)
