Rossi, Peter E.: Bayesian non- and semi-parametric methods and applications

Abstract

This book demonstrates the flexibility and accuracy of the Bayesian approach towards nonand semi-parametric statistical modelling. As the Bayesian approach offers flexible yet parsimoniously parameterized statistical model specifications, it is well suited for empirical analysis. Although the book is not always perfect stringent with regard to notation, it provides a concise and very readable access for readers who would like to become familiar with the application of Bayesian techniques in the context of nonand semi-parametric statistical modelling. The presented material documents the author’s profound mastership in providing access to the most advanced topics of statistical analysis without stepping over operational complexity or losing rigour. It highlights all involved important topics that arise in the context of nonand semiparametric Bayesian settings and it is well suited to motivate empirical researchers to adapt these techniques. Using finite mixture distributions as one core element, Rossi elaborates thoroughly on advantages as well as on caveats of the Bayesian approach and its implementation in such a way that the book serves also as a source of reference related to the abundant illustrated applications, carefully provided from microeconomics, behavioral. The book contains six chapters. Chapter 1 introduces the concept of finite normal mixture distributions. Next to a short review of Maximum Likelihood estimation, facilitated via the Expectation-Maximization algorithm, the Bayesian estimation approach, facilitated byMarkovChainMonteCarlo (MCMC) techniques, is discussed. Thereby, attention is paid to the important issue of label switching occurring in the absence of identifying constraints on the parameter space. Relabeling algorithms, as discussed by Stephens (2000) and Celeux et al. (2000), are shortly discussed as devices to base inference on the output of the unconstrained sampler. Also the different