Bayesian analysis of logistic regression with an unknown change point and covariate measurement error

We discuss Bayesian estimation of a logistic regression model with an unkno wn threshold limiting value (TLV). In these models it is assumed that there is no effect of a covariate on the response under a certain unknown TLV. T he estimation of these models in a Bayesian context by Markov chain Monte C arlo (MCMC) methods is considered with focus on the TLV. We extend the mode l by accounting for measurement error in the covariate. The Bayesian soluti on is compared with the likelihood solution proposed by Kuchenhoff and Carr oll using a data set concerning the relationship between dust concentration in the working place and the occurrence of chronic bronchitis. Copyright ( C) 2001 John Wiley & Sons, Ltd.