Sequentially additive nonignorable missing data modelling using auxiliary marginal information

DOI10.1093/BIOMET/ASZ054MaRDI QIDQ5212912zbMATH OpenOpenAlexWikidataFDO

Authors Mauricio Sadinle, Jerome P. Reiter

Publication date 30 January 2020

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1902.06043

zbMATH Keywords

information projectionmissing not at randomnonmonotone nonresponsenonparametric identificationobservational equivalence

Mathematics Subject Classification ID

Missing data (62D10) Estimation in multivariate analysis (62H12) Sequential statistical analysis (62L10)

Abstract: We study a class of missingness mechanisms, called sequentially additive nonignorable, for modeling multivariate data with item nonresponse. These mechanisms explicitly allow the probability of nonresponse for each variable to depend on the value of that variable, thereby representing nonignorable missingness mechanisms. These missing data models are identified by making use of auxiliary information on marginal distributions, such as marginal probabilities for multivariate categorical variables or moments for numeric variables. We present theory proving identification results, and illustrate the use of these mechanisms in an application.

Recommendations

• Sequential identification of nonignorable missing data mechanisms
• Itemwise conditionally independent nonresponse modelling for incomplete multivariate data
• Analysis of multivariate missing data with nonignorable nonresponse
• A latent class selection model for nonignorably missing data
• On the identifiability and estimation of generalized linear models with parametric nonignorable missing data mechanism

Cited in

(13)

• On classification with nonignorable missing data
• On the maximal deviation of kernel regression estimators with NMAR response variables
• Using Auxiliary Data for Parameter Estimation with Non-Ignorably Missing Outcomes
• Sequential identification of nonignorable missing data mechanisms
• Sequential imputation for models with latent variables assuming latent ignorability
• On regression and classification with possibly missing response variables in the data
• A kernel-type regression estimator for NMAR response variables with applications to classification
• On nonparametric functional data regression with incomplete observations
• On nonparametric regression with incomplete data via inverse-weighting and their convergence in L_p norms
• A multiple imputation method using population information
• A note on convergence of calibration weights to inverse probability weights
• Strong optimality of kernel functional regression in L^p norms with partial response variables and applications
• Leveraging auxiliary information on marginal distributions in nonignorable models for item and unit nonresponse

This page was built for publication: Sequentially additive nonignorable missing data modelling using auxiliary marginal information

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5212912)