Likelihood, Bayesian, and MCMC methods in quantitative genetics

From MaRDI portal





The aim of this book is to give the key ideas underlying likelihood and Bayesian inference in statistical genetics, with particular emphasis on Markov chain Monte Carlo (MCMC) methods, so that they are accessible to numerate biologists. Derivations are given in great detail, and the examples used are generally from quantitative genetics, including animal breeding, and are fully worked out. The book is organised into four parts as follows. Part I gives a review of probability and distribution theory, while Part II introduces methods of statistical inference. Part III gives the background to MCMC, and detailed discussion of MCMC procedures, including the Metropolis-Hastings algorithm, the Gibbs sampler and reversible jump MCMC, and finally overviews methods for analysing MCMC output including convergence issues and sensitivity analysis. The final Part presents some of the models that currently are being used in quantitative genetics. The treatment is mainly Bayesian and the models are implemented via MCMC. They include mixed models for single- and multiple-trait analyses, analyses involving ordered categorical traits based on Wright's threshold model, models for analysis of longitudinal data, segregation analysis and models for the detection of quantitative trait loci.




Cited in
(35)








This page was built for publication: Likelihood, Bayesian, and MCMC methods in quantitative genetics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q700445)