Bayesian Statistics: An Introduction - Couverture rigide

Lee, Peter M.

Couverture rigide

ISBN 10 : 0852642989 ISBN 13 : 9780852642986

Editeur : Hodder Arnold, 1989

Synopsis

Statistics is concerned with investigating the degree of confidence we can have in various hypotheses. The Bayesian approach is distinguished by giving each hypothesis a probability and then modifying it in the light of the experimental data. This is controversial because for a new theory with no data available, an element of guesswork has to be involved. The author presents the ideas behind Bayesian statistics at a level suitable for advanced undergraduate or postgraduate students. The discrepancies between the conclusions of Bayesian and classical statistics are highlighted.

A propos du livre

Présentation de l'éditeur

Bayesian Statistics is the school of thought that uses all information surrounding the likelihood of an event rather than just that collected experimentally. Among statisticians the Bayesian approach continues to gain adherents and this new edition of Peter Lee's well-established introduction maintains the clarity of exposition and use of examples for which this text is known and praised.
In addition, there is extended coverage of the Metropolis-Hastings algorithm as well as an introduction to the use of BUGS (Bayesian Inference Using Gibbs Sampling) as this is now the standard computational tool for such numerical work. Other alterations include new material on generalized linear modelling and Bernardo's theory of reference points.

Présentation de l'éditeur

Among statisticians the Bayesian approach continues to gain adherents and so it is appropriate that Peter Lee has updated and expanded his successful introduction to the subject in this second edition. An additional chapter has been added which deals with hierarchical methods in Bayesian statistics and gives a fuller treatment of empirical Bayes methods. Another chapter deals with real numerical methods, especially the EM algorithm and Gibbs sampling. Other alterations have been made throughout the text, including the addition of a brief description of Bayes linear methods, and the number of exercises has been considered increased.

Détails de l'édition

• Éditeur: Hodder Arnold
• Date d'édition: 1989
• Langue: anglais
• ISBN 10: 0852642989
• ISBN 13: 9780852642986
• Reliure: Relié
• Nombre de pages: 304
• Coordonnées du fabricant: non disponible
• Personne responsable: non disponible