(Wiley series in Probability and Mathematical Statistics: Applied
Probability
and Statistics Section)
by G.J. McLachlan and D. Peel. New York; John Wiley
& Sons, Inc. 2000, xvii + 274 pp.
ISBN 0-471-00626-2.
Extracts from Published Reviews:
Everitt
(2002, Statistical Methods in Medical Research)
"The book by McLachlan and Peel is a masterly overview of the area, which
manages the difficult task of integrating the technical and the
practical almost seamlessly, so that the material included should appeal
to a variety of statisticians ranging form those interested in the minutia
of the convergence properties of the EM algorithm to those more concerned
when deciding how many components to include when modelling a particular
data set. ...
"This is a scholarly and authoritative account of finite mixture
distributions, well written and containing many interesting examples. It
is difficult to ask for more and there is no doubt that McLachlan and
Peel's book will be the standard reference on mixture models for many
years to come.
Karlis
(2002,
Zentralblatt fur Mathematik und ihre Grenzgebiete)
# 0963.62061
"The book will become popular to many researchers as it provides a
complete, up to date coverage of the topic and also discusses problems
that may be further pursued by researchers in the forthcoming years.
... they (students) will love the fact that the material covered is so
wide that it will make this book a standard reference for the forthcoming
years."
Kemp
(2002, Journal of the Royal Statistical Society
Series D (The Statistician)
"The publication in 1988 of McLachlan and Basford's Mixture Models:
Inference and Applications to Clustering herladed much interest in
applications of mixture models, in developments such as multinomial,
hidden Markov chain, and hidden Markov random field models, and in the
computer estimation of such models. ... McLachlan and Peel aim to draw the
subject together in book form. They are to be congratulated on the extent
of their achievement. ...
This book resembles an encyclopaedia. From Chapter 2 onwards, the chapters
are like articles - they are largely stand alone and nearly all give an
encyclopaedic coverage of a particular aspect of the fitting of mixture
models.
If you are the sort of person who needs to own this book, then you
probably know about it already. If you are not, then you should realize
that this is an important area of statistics that currently commands much
interest. Try to persuade your library to buy a copy."
Ryden
(2002, Mathematical Reviews)
"This book is excellent reading as an introduction to finite mixture
modelling in a very broad sense. All chapters contain carefully described
and worked out examples to illustrate the methodology. All subjects are not
treated exhaustively, which is only natural considering the wide range of
topics covered by the book, but there are always ample references given to
further reading. Hence I imagine that the book should also serve as an
excellent handbook on mixture modelling for the applied statistician."
Shanmugam
(2002, Technometrics)
"The book provides an extensive review on finite mixture modeling focusing
on the computational aspect of using such models in practice. ...
This is an excellent book for those who are engaged in research work in
modeling multimodal data. It contains up-to-date developments in finite
mixtures of distributions which are used to describe multimodal data. ...
I enjoyed (especially the chapters about the number of components in
mixture models, hidden Markov models) reading this book. I recommend
it highly to both mathematical and applied statisticians."