Markov chain Monte Carlo in practice : interdisciplinary statistics

Więcej o książce

In a family study of breast cancer, epidemiologists in Southern California enhance the detection of gene-environment interactions. A study in Gambia aids a vaccination program in reducing Hepatitis B carriage. Archaeologists in Austria accurately date a Bronze Age site, while researchers in France map a rare disease with minimal variation. Each study utilizes Markov chain Monte Carlo (MCMC) methods for more accurate results. Recent developments in general state-space Markov chain theory have made these methods more accessible and powerful for statisticians. This work introduces MCMC methods and their applications, alongside theoretical background. The authors, noted contributors to MCMC methodology, focus on practical applications, minimizing technical jargon for a broad audience. Examples range from basic Gibbs sampling to more complex applications. The first chapter equips readers to begin applying MCMC, while subsequent chapters address key issues, concepts, implementation techniques, performance improvement, model adequacy assessment, and application domains. This comprehensive introduction highlights the significance of MCMC across various fields, including archaeology, astronomy, biostatistics, genetics, epidemiology, and image analysis, laying a strong foundation for its application in other areas.