Formal and informal model selection with incomplete data

DOI10.1214/07-STS253zbMATH Open1327.62027arXiv0808.3587OpenAlexW3101527867MaRDI QIDQ900458FDOQ900458

Authors: Geert Verbeke, Caroline Beunckens, Geert Molenberghs 

Publication date: 22 December 2015

Published in: Statistical Science (Search for Journal in Brave)

Abstract: Model selection and assessment with incomplete data pose challenges in addition to the ones encountered with complete data. There are two main reasons for this. First, many models describe characteristics of the complete data, in spite of the fact that only an incomplete subset is observed. Direct comparison between model and data is then less than straightforward. Second, many commonly used models are more sensitive to assumptions than in the complete-data situation and some of their properties vanish when they are fitted to incomplete, unbalanced data. These and other issues are brought forward using two key examples, one of a continuous and one of a categorical nature. We argue that model assessment ought to consist of two parts: (i) assessment of a model's fit to the observed data and (ii) assessment of the sensitivity of inferences to unverifiable assumptions, that is, to how a model described the unobserved data given the observed ones.

Full work available at URL: https://arxiv.org/abs/0808.3587

Recommendations

• Selection Models and Pattern‐Mixture Models for Incomplete Data with Covariates
• Bayesian model selection for incomplete data using the posterior predictive distribution
• Sensitivity analysis for incomplete categorical data
• Stochastic complexity and model selection from incomplete data
• The E-MS algorithm: model selection with incomplete data

zbMATH Keywords

missing at randomsensitivity analysislinear mixed modelmultivariate normalmissing not at randominterval of ignorance

Mathematics Subject Classification ID

Cites Work

• Title not available (Why is that?)
• Likelihood based frequentist inference when data are missing at random
• Principal stratification in causal inference
• Identification of Causal Effects Using Instrumental Variables
• Title not available (Why is that?)
• Estimation and Comparison of Changes in the Presence of Informative Right Censoring by Modeling the Censoring Process
• Inference and missing data
• Title not available (Why is that?)
• Adjusting for Nonignorable Drop-Out Using Semiparametric Nonresponse Models
• Title not available (Why is that?)
• Title not available (Why is that?)
• Linear mixed models for longitudinal data
• Every Missingness not at Random Model Has a Missingness at Random Counterpart with Equal Fit
• The central role of the propensity score in observational studies for causal effects
• Statistics and Causal Inference
• Estimation of Regression Coefficients When Some Regressors Are Not Always Observed
• Title not available (Why is that?)
• Semiparametric Regression for Repeated Outcomes with Nonignorable Nonresponse
• Informative Drop-Out in Longitudinal Data Analysis
• Models for discrete longitudinal data.
• Analyzing incomplete longitudinal clinical trial data
• Unbalanced Repeated-Measures Models with Structured Covariance Matrices
• Pattern-Mixture Models for Multivariate Incomplete Data
• A generalized multivariate analysis of variance model useful especially for growth curve problems
• Ignorance and uncertainty regions as inferential tools in a sensitivity analysis
• Title not available (Why is that?)
• Local Influence in Linear Mixed Models
• Title not available (Why is that?)
• Pattern-mixture models with proper time dependence
• Title not available (Why is that?)
• Semiparametric Efficiency in Multivariate Regression Models with Missing Data
• Title not available (Why is that?)
• A class of pattern-mixture models for normal incomplete data
• Multiple Imputation for Model Checking: Completed‐Data Plots with Missing and Latent Data
• Design sensitivity analysis of structural systems
• Diagnostics for Mixed-Model Analysis of Variance
• On structural equation modeling with data that are not missing completely at random
• Strategies to fit pattern-mixture models
• The nature of sensitivity in monotone missing not at random models
• Linear mixed models in practice: a SAS-oriented approach
• A Semi‐Parametric Shared Parameter Model to Handle Nonmonotone Nonignorable Missingness
• Monotone missing data and pattern‐mixture models
• Intent-to-Treat Analysis for Longitudinal Studies with Drop-Outs
• Methods for conducting sensitivity analysis of trials with potentially nonignorable competing causes of censoring
• Estimation and comparison of Changes in the Presence of Informative Right Censoring: Conditional Linear Model
• Analysis of Longitudinal Data with Non-Ignorable Non-Monotone Missing Values
• Shared parameter models under random effects misspecification
• Pattern-Mixture Models for Multivariate Incomplete Data with Covariates
• Sensitivity analysis for incomplete categorical data
• Sensitivity analysis for nonrandom dropout: a local influence approach
• Sensitivity Analysis for Incomplete Contingency Tables: The Slovenian Plebiscite Case
• A Latent‐Class Mixture Model for Incomplete Longitudinal Gaussian Data
• Influence analysis to assess sensitivity of the dropout process.
• Title not available (Why is that?)
• A local influence approach applied to binary data from a psychiatric study
• Selection Models and Pattern‐Mixture Models for Incomplete Data with Covariates
• Title not available (Why is that?)
• Analyzing incomplete discrete longitudinal clinical trial data
• Pseudo-Likelihood for Combined Selection and Pattern-Mixture Models for Incomplete Data
• Title not available (Why is that?)
• Assessing Response Profiles from Incomplete Longitudinal Clinical Trial Data Under Regulatory Considerations

Cited In (3)

• Incomplete tests of conditional association for the assessment of model assumptions
• Rejoinder to the comments on: Missing data methods in longitudinal studies: a review
• Multiple-imputation-based residuals and diagnostic plots for joint models of longitudinal and survival outcomes

This page was built for publication: Formal and informal model selection with incomplete data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q900458)