Readership: Graduate students and researchers in statistics.

Table of contents. Chapter 1: Introduction, Chapter 2: Model‐based Clustering: Basic Ideas, Chapter 3: Dealing with Difficulties, Chapter 4: Model‐based Classification, Chapter 5: Semi‐supervised Clustering and Classification, Chapter 6: Discrete Data Clustering, Chapter 7: Variable Selection, Chapter 8: High‐dimensional Data Chapter, 9: Non‐Gaussian Model‐based Clustering, Chapter 10: Network Data, Chapter 11: Model‐based Clustering with Covariates, Chapter 12: Other Topics

Model‐based clustering and classification are important modern topics. This advanced text explains the underlying concepts clearly and is strong on theory. In an ideal world, this excellent theoretical basis would be accompanied by insightful data analyses to illustrate the methods, informative graphics to complement the analyses and supporting R code. Unfortunately, the data analyses in the current text are disappointing and are occasionally flawed; the graphics are weak with little use of modern display, often too small, with poor choice of colour and symbols, and the relevant accompanying text two or more pages away. The R codes are often incomplete and sometime fail to run, a surprising and unfortunate feature in this age of reproducible research.

If you are interested in the model‐based approach (and you should be, if you are interested in clustering and classification), then this book is for you. I congratulate the authors on the theoretical aspects of their book, it's a fine achievement. The application component of the book does not match up to the theoretical counterpart. Details of the issues the reviewer has found have been sent to the authors so that they are able to rectify the errors in the next edition. Once that is accomplished, this book will make a fine contribution in the area of clustering and classification.

读者群：统计专业的研究生和研究人员。

目录。第1章：简介，第2章：基于模型的聚类：基本概念，第3章：处理困难，第4章：基于模型的分类，第5章：半监督聚类和分类，第6章：离散数据聚类，第7章：变量选择，第8章：高维数据，第9章：基于非高斯模型的聚类，第10章：网络数据，第11章：基于协变量的基于模型的聚类，第12章：其他主题

基于模型的聚类和分类是重要的现代主题。这篇高级文章清楚地解释了基本概念，并且在理论上很强。在理想的世界中，这种出色的理论基础将伴随着有洞察力的数据分析以举例说明方法，提供信息丰富的图形以补充分析并支持R代码。不幸的是，当前文本中的数据分析令人失望，并且有时存在缺陷。图形很弱，很少使用现代显示，通常太小，颜色和符号选择不当，并且相关的附带文本两页或更多页。R代码通常不完整，有时无法运行，这是可重复研究时代令人惊讶和不幸的特征。

如果您对基于模型的方法感兴趣（如果您对聚类和分类感兴趣，则应该如此），那么本书非常适合您。我祝贺作者的理论观点，这是一个很好的成就。本书的应用部分与理论上的部分不符。已将审稿人发现的问题的详细信息发送给作者，以便他们能够在下一版中更正错误。一旦完成，这本书将在聚类和分类领域做出出色的贡献。