Bayesian Latent Pattern Mixture Models for Handling Attrition in Panel Studies With Refreshment Samples

  title={Bayesian Latent Pattern Mixture Models for Handling Attrition in Panel Studies With Refreshment Samples},
  author={Yajuan Si and Jerome P. Reiter and D. Sunshine Hillygus},
  journal={arXiv: Methodology},
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… 

Figures and Tables from this paper

Statistical Modeling of Longitudinal Data with Non-ignorable Non-monotone Missingness with Semiparametric Bayesian and Machine Learning Components.
The methodology is applied to data from a phase II clinical trial that studies quality of life of patients with prostate cancer receiving radiation therapy, and improves existing methods by accommodating data with small sample size.
Leveraging auxiliary information on marginal distributions in nonignorable models for item and unit nonresponse
A model‐based framework is used to impute missing values in voter turnout in a subset of data from the US Current Population Survey to examine the results to different assumptions about the unit and item nonresponse.
Bayesian Profiling Multiple Imputation for Missing Electronic Health Records
This work proposes an individualized Bayesian latent profiling approach to capture A1c measurement trajectories subject to missingness under the framework of multiple imputation (MI), which is computationally efficient and fits flexible models that provide useful clinical insights.
Development of a common patient assessment scale across the continuum of care: A nested multiple imputation approach
A two-step procedure is proposed that combines nested multiple imputation with the multivariate ordinal probit (MVOP) model to obtain a common patient assessment scale across the post-acute care continuum and shows that, for all of the estimands considered, and in most of the experimental conditions, the MVOP model appears to be superior.
Combining Information from Multiple Sources in Bayesian Modeling
Statistics) Combining Information from Multiple Sources in Bayesian Modeling combines information from multiple sources inBayesian modeling to derive conclusions about posterior probability distributions.
Nonresponse Bias Analysis in Longitudinal Educational Assessment Studies
Her research interests include Bayesian statistics, survey inference, missing data imputation, and data confidentiality protection. His research interests include incomplete data, sample surveys,


Semi-parametric Selection Models for Potentially Non-ignorable Attrition in Panel Studies with Refreshment Samples
A Bayesian approach to handle attrition in two-wave panels with one refreshment sample and many categorical survey variables is presented and a model to correct attrition bias is applied in an analysis of data from the 2007–08 Associated Press/Yahoo News election panel study.
Handling attrition in longitudinal studies: The case for refreshment samples
This work review and bolster the case for the use of refreshment samples in panel studies, including examples of both a fully Bayesian approach for analyzing the concatenated panel and refreshment data, and a multiple imputation approach for analyzed only the original panel.
Inference in panel data models under attrition caused by unobservables
Accounting for Nonignorable Unit Nonresponse and Attrition in Panel Studies with Refreshment Samples
This work presents an approach that facilitates sensitivity analyses for suspected nonignorable unit nonresponse in the initial wave of the panel and in the refreshment sample itself, and illustrates the approach using simulation studies and an analysis of data from the 2007-2008 Associated Press/Yahoo News election panel study.
Combining Panel Data Sets with Attrition and Refreshment Samples
The manner in which the presence of refreshment samples allows the researcher to test various models for attrition in panel data, including models based on the assumption that missing data are missing at random are described.
A General Class of Pattern Mixture Models for Nonignorable Dropout with Many Possible Dropout Times
This article proposes a marginally specified latent class pattern mixture model, where the marginal mean is assumed to follow a generalized linear model, whereas the mean conditional on the latent class and random effects is specified separately.
Reparameterizing the Pattern Mixture Model for Sensitivity Analyses Under Informative Dropout
A reparameterization of the pattern mixture model is proposed that allows investigation of sensitivity to assumptions about nonidentified parameters in both the mean and variance, allows consideration of a wide range of nonignorable missing-data mechanisms, and has intuitive appeal for eliciting plausible missing- data mechanisms.
Latent Pattern Mixture Models for Informative Intermittent Missing Data in Longitudinal Studies
A latent pattern mixture model (LPMM) is proposed, where the mixture patterns are formed from latent classes that link the longitudinal response and the missingness process and suggests the presence of four latent classes linking subject visit patterns to homeless outcomes.
Modeling longitudinal data with nonignorable dropouts using a latent dropout class model.
  • J. Roy
  • Mathematics
  • 2003
This work proposes an alternative approach to pattern-mixture models with dropout, which is a latent-class model, where the dropout time is assumed to be related to the unobserved (latent) class membership; a regression model for the response is specified conditional on the latent variable.
Panel Conditioning and Attrition in the AP-Yahoo! News Election Panel Study
This paper examines the potential for attrition bias and panel conditioning in a longitudinal online election panel survey. The 2008 Associated Press-Yahoo! News Poll was conducted by Knowledge