• Hardcover: 320 pages
• Publisher: Cambridge University Press; 1 edition (July 28, 2008)
• Language: English
• ISBN-10: 0521852250Editorial ReviewsReview"All data analyses are compatible with open-source R software, and data sets and R code are available from a companion web site."
  Book News
  
  "Overall, given the inviting style of the presentation and the quality of the material, this book could be quite a catch for graduate students as well as for practitioners where models really do make a difference."
  Ita Cirovic Donev, MAA Reviews
  
  "'This is a good textbook for a master-level statistical course about model selection.' It covers many important concepts and methods about model selection."
  Mathematical Reviews
  
  "This book is comprehensive in its treatment of the subject and will probably teach something new, even to the most experienced researchers in model selection. The authors have succeeded in bringing together a coherent volume, which gives a state of the art account of the current practice in model selection and comparison, containing a plethora of asymptotic (sometimes new) results, which can be used to compare different model choice criteria. Most importantly, this is the sole volume dedicated to this subject, taking a fully statistical as opposed to an information theoretic approach to the topic of model selection. This book will be attractive to a wide range of graduate students and researchers, users or developers of model choice criteria, of all statistical persuasions."
  Cedric E. Ginestet, Statistics in Society
  
  Product DescriptionChoosing a model is central to all statistical work with data. We have seen rapid advances in model fitting and in the theoretical understanding of model selection, yet this book is the first to synthesize research and practice from this active field. Model choice criteria are explained, discussed and compared, including the AIC, BIC, DIC and FIC. The uncertainties involved with model selection are tackled with discussions of frequent and Bayesian methods; model averaging schemes are presented. Real-data examples are complemented by derivations pr3 of 4 people found the following review helpful:
  5.0 out of 5 stars this is an excellent book, June 29, 2009
  

  By	Nils Lid Hjort (Norway) - See all my reviews (REAL NAME)

  
  This review is from: Model Selection and Model Averaging (Cambridge Series in Statistical and Probabilistic Mathematics) (Hardcover)
  Well, I'm biased, since I'm the author -- but I do nevertheless think it's excellent. Part of the reason is that it touches topics that I consider "mainstream and important" for the modern statistician.
  
  One needs to be able not only to take any reasonable model (or often enough actually invent a new one, for its specific purpose) and fit it to one's data, complete with interpretation, parameter estimates, and assessment of their precision; but one needs to compare such a model with other candidate models, and somehow converge to a reasonable decision of the type "model seven appears to be better than the other nine I tried out, for these & these specific reasons". The book also pushes the idea that you need to be conscious about the specific use to which the selected model will be put -- a good model for mean structure (often arrived at using the AIC, say) may not do a good job for you if you are more interested in say skewness or extreme aspects; hence the FIC (the Focussed Information Criterion).
  
  This "mainstream and important" aspect has been appreciated when I've been teaching this material, either qua full one-semester course [...] or via say two-day short courses. I have "happy customers" backing up my claim of its usefulness, not only to the theoretically inclined mathematical statisticians (a stratum to which I belong) but also to the so-called practitioners out there.
  
  We've also been complimented for the generous & broad list of real world data examples, ranging from a Nobel Prize quarrel (between Sholokhov and Solzhenitsyn) and life times in Roman Era Egypt to the (almost!) exponential decrease of beer foam and World Cup Football match prediction. We also include a thorough & enlightened discussion of The Quiet Scandal of Statistics.
  
  So, yes, I do hope you buy the book & benefit from using it (and encourage both complimenting and complementing opinions).
  
  Nils Lid Hjort
  Professor of mathematical statistics, Department of Mathematics, University of Oslo, Norwayoviding deeper insight into the methodology, and instructive exercises build familiarity with the methods. The companion website features Data sets and R-code.
  
• ISBN-13: 978-0521852258