Format

Send to

Choose Destination
See comment in PubMed Commons below
Stat Methods Med Res. 2016 Oct;25(5):1836-1853. Epub 2013 Oct 9.

Robust inference for mixed censored and binary response models with missing covariates.

Author information

1
Novartis Healthcare Pvt. Ltd., Hyderabad, India.
2
Department of Statistics, University of Calcutta, Calcutta, India.
3
School of Mathematics and Statistics, Carleton University, Ottawa, ON, Canada sinha@math.carleton.ca.

Abstract

In biomedical and epidemiological studies, often outcomes obtained are of mixed discrete and continuous in nature. Furthermore, due to some technical inconvenience or else, continuous responses are censored and also a few covariates cease to be observed completely. In this paper, we develop a model to tackle these complex situations. Our methodology is developed in a more general framework and provides a full-scale robust analysis of such complex models. The proposed robust maximum likelihood estimators of the model parameters are resistant to potential outliers in the data. We discuss the asymptotic properties of the robust estimators. To avoid computational difficulties involving irreducibly high-dimensional integrals, we propose a Monte Carlo method based on the Metropolis algorithm for approximating the robust maximum likelihood estimators. We study the empirical properties of these estimators in simulations. We also illustrate the proposed robust method using clustered data on blood sugar content from a clinical trial of individuals who were investigated for diabetes.

KEYWORDS:

binary model; censored regression model; expectation maximization algorithm; metropolis algorithm; missing data; robust estimation

PMID:
24108268
DOI:
10.1177/0962280213503924
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Atypon
    Loading ...
    Support Center