Model checking for partially linear models with missing responses at random

In this paper, we investigate the model checking problem for a partial linear model while some responses are missing at random. By imputation and marginal inverse probability weighted methods, two completed data sets are constructed. Based on the two completed data sets, we build two empirical proce...

Full description

Saved in:
Bibliographic Details
Published in:Journal of multivariate analysis Vol. 100; no. 4; pp. 636 - 651
Main Authors: Sun, Zhihua, Wang, Qihua, Dai, Pengjie
Format: Journal Article
Language:English
Published: Amsterdam Elsevier Inc 01.04.2009
Elsevier
Taylor & Francis LLC
Series:Journal of Multivariate Analysis
Subjects:
62F03
62F03 62G10 Model checking Response missing at random Imputation Inverse probability weighting Empirical process Re-sampling
62G10
Approximation
Asymptotic methods
Distribution theory
Empirical process
Exact sciences and technology
Imputation
Inverse probability weighting
Mathematical models
Mathematics
Model checking
Multivariate analysis
Parametric inference
Probability and statistics
Probability theory and stochastic processes
Re-sampling
Response missing at random
Sampling techniques
Sciences and techniques of general use
Simulation
Statistics
Studies
Re-sampling
Empirical process
Model checking
Inverse probability weighting
Response missing at random
62G10
Imputation
62F03
Statistical distribution
Response model
Probability distribution
Multivariate analysis
Linear model
Hypothesis test
Statistical test
Marginal distribution
Distribution function
Approximation theory
Sampling
Approximation
Test statistic
Asymptotic behavior
Finite sample
Probability
Statistical method
Missing data
Simulation
ISSN:0047-259X, 1095-7243
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we investigate the model checking problem for a partial linear model while some responses are missing at random. By imputation and marginal inverse probability weighted methods, two completed data sets are constructed. Based on the two completed data sets, we build two empirical process-based tests for examining the adequacy of partial linearity of the model. The asymptotic distributions of the test statistics under the null hypothesis and local alternative hypotheses are obtained respectively. A re-sampling approach is applied to obtain the approximation to the null distributions of the test statistics. Simulation results show that the proposed tests work well and both proposed methods have better finite sample properties compared with the complete case (CC) analysis which discards all the subjects with missing data.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ISSN:0047-259X
1095-7243
DOI:10.1016/j.jmva.2008.07.002