Literature DB >> 21114712

Bayesian sensitivity models for missing covariates in the analysis of survival data.

Karla Hemming1, Jane Luise Hutton.   

Abstract

RATIONALE: This paper presents a Bayesian approach using WinBUGS for analysing survival data in which observations have missing information on some covariates. Modelling the joint density of the survival time and the covariates allows for the missing covariate data to be missing at random (MAR), as opposed to the more restrictive assumptions imposed by a complete case analysis.
METHODS: Here, the survival times are modelled by the accelerated failure time model and the joint covariate density is factorized as a series of conditional densities, each modelled by logistic regression. We propose a class of models to examine MAR assumption by using Bayesian informative priors or auxiliary data.
RESULTS: In the example considered, the complete case analysis underestimates the proportion of severely impaired cases. Furthermore, models evaluating sensitivity to the MAR assumption suggest that median life expectancies could be increased. Gains in precision are small in the application considered, possibly a reflection of extra uncertainty because of the inclusion of all cases, including those of unknown severity.
CONCLUSIONS: Through simple Bayesian models, more realistic assumptions concerning the nature of the missing data can be made. Implementation in WinBUGS means that this model is accessible to practicing statisticians.
© 2010 Blackwell Publishing Ltd.

Entities:  

Mesh:

Year:  2010        PMID: 21114712     DOI: 10.1111/j.1365-2753.2010.01569.x

Source DB:  PubMed          Journal:  J Eval Clin Pract        ISSN: 1356-1294            Impact factor:   2.431


  4 in total

1.  A Bayesian Vector Autoregressive Model with Nonignorable Missingness in Dependent Variables and Covariates: Development, Evaluation, and Application to Family Processes.

Authors:  Linying Ji; Meng Chen; Zita Oravecz; E Mark Cummings; Zhao-Hua Lu; Sy-Miin Chow
Journal:  Struct Equ Modeling       Date:  2020       Impact factor: 6.125

2.  Subsample ignorable likelihood for accelerated failure time models with missing predictors.

Authors:  Nanhua Zhang; Roderick J Little
Journal:  Lifetime Data Anal       Date:  2014-08-05       Impact factor: 1.588

3.  A calibrated Bayesian method for the stratified proportional hazards model with missing covariates.

Authors:  Soyoung Kim; Jae-Kwang Kim; Kwang Woo Ahn
Journal:  Lifetime Data Anal       Date:  2022-01-16       Impact factor: 1.588

4.  Effects of growth rate, size, and light availability on tree survival across life stages: a demographic analysis accounting for missing values and small sample sizes.

Authors:  Aristides Moustakas; Matthew R Evans
Journal:  BMC Ecol       Date:  2015-02-28       Impact factor: 2.964

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.