Topics in Bayesian models with ordered parameters : response misclassification, covariate misclassification, and sample size determination.

Researchers often analyze data assuming models with constrained parameters. Order constrained parameters are of particular interest. In this dissertation, we examine three Bayesian models which incorporate ordered parameters. We investigate ordered differential response misclassification in a logistic regression model and provide an adjustment for it using a conditional prior structure. We examine a parametric Bayesian Weibull proportional hazards model with ordered covariate misclassification and provide an adjustment for it. Finally, we consider informative hypotheses (Hoijtink, 2012) and perform sample size determination for this problem using the two priors approach of Brutti et al. (2008).