Bayesian approach to errors-in-variables in count data regression models with departures from normality and overdispersion

Rozliman, Nur Aainaa and Ibrahim, Adriana Irawati Nur and Yunus, Rossita Muhamad (2018) Bayesian approach to errors-in-variables in count data regression models with departures from normality and overdispersion. Journal of Statistical Computation and Simulation, 88 (2). pp. 203-220. ISSN 0094-9655

Full text not available from this repository.
Official URL: https://doi.org/10.1080/00949655.2017.1381845

Abstract

In most practical applications, the quality of count data is often compromised due to errors-in-variables (EIVs). In this paper, we apply Bayesian approach to reduce bias in estimating the parameters of count data regression models that have mismeasured independent variables. Furthermore, the exposure model is misspecified with a flexible distribution, hence our approach remains robust against any departures from normality in its true underlying exposure distribution. The proposed method is also useful in realistic situations as the variance of EIVs is estimated instead of assumed as known, in contrast with other methods of correcting bias especially in count data EIVs regression models. We conduct simulation studies on synthetic data sets using Markov chain Monte Carlo simulation techniques to investigate the performance of our approach. Our findings show that the flexible Bayesian approach is able to estimate the values of the true regression parameters consistently and accurately.

Item Type: Article
Uncontrolled Keywords: Count data regression; errors-in-variables; Bayesian; Markov chain Monte Carlo
Subjects: Q Science > Q Science (General)
Q Science > QA Mathematics
Divisions: Faculty of Science > Institute of Mathematical Sciences
Depositing User: Ms. Juhaida Abd Rahim
Date Deposited: 09 Apr 2019 07:58
Last Modified: 09 Apr 2019 07:58
URI: http://eprints.um.edu.my/id/eprint/20861

Actions (login required)

View Item View Item