On the Bayesian estimator of interaction models with measurement error and misclassification in covariates

Sultana, Mahbuba (2018) On the Bayesian estimator of interaction models with measurement error and misclassification in covariates. Masters thesis, Memorial University of Newfoundland.

[English] PDF - Accepted Version Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. Download (1MB)

Abstract

Measurement error and misclassification in covariates are commonly arising problems in statistical models. They have negative impacts on statistical inference about the outcome, including bias and large variability in estimators. Furthermore, in a statistical model, two or more covariates can interact, which in practice is quite challenging to deal with. One of the recent techniques is Bayesian method that incorporates the prior knowledge about parameters. In this research, Bayesian techniques are applied to the models with interaction terms, while addressing measurement error and misclassification. Moreover, through extensive simulation studies, Markov Chain Monte Carlo algorithms are used to implement the Bayesian methods.

Actions (login required)

View Item