這本書可分為機率與統計兩部分，機率部分對於已經好好地修過「機率導論」的同學而言有些簡單；而後半的統計部分，我認為已涵蓋重要的課題，教學使用及學生自習上都還可以，沒有什麼大問題。但統計現今的發展面向十分多元化，雖然書中對這些較新的研究發展有略微提到，我認為如果能再講的多一些、深入一些會更好。習題部分我認為習題難度也適中，足夠讓同學有充分練習的機會。
修這門課的學生除了熟讀這本教科書，做習題外，可以針對自己有興趣的部分，找相關的書或論文研讀，增進學習效果。與早期的學生相比較，學生比較不好奇。在資源貧乏的時代，常習慣於追求更多的資源及機會，在資源豐裕的時代，因隨時可取得資源，如沒有好奇心，不去使用資源，反而較資源貧乏時代的學生享受更少的資源及機會。[陳宏老師]
The authors have written an innovative, creative and interesting textbook on theoretical statistics in which they have integrated modern concepts such as errors in variables, Stein estimation, decision theory and Bayesian analysis without departing radically from standard mathematical statistics. They accomplish this by logical development, proofs and ideas from the basics of probability theory. This is an excellent mathematical statistics textbook with a unique blend of mathematical rigor, historical perspective and modern concepts. The authors' presentation of the material is very clear and the level of the book is slightly higher than other popular textbooks, such as those of Hogg and Craig (1970), Lindgren (1968) and Mood, Graybill and Boes (1974). The book is primarily intended as a text for first-year graduate students majoring in statistics or in a field where statistics concentration is desirable. A year of calculus and some knowledge of matrix algebra would suffice for most of the material covered. Each chapter has an introduction that describes the nature of the materials covered, how it relates to the previous material and how it will be used in later chapters. Exercises at the end of each chapter are an integral part of the book and range in difficulty from routine calculations to up-to-date theoretical results. The exercises extend from early classic probability problems to recent problems on set estimation, Bayesian methods and Stein-type estimation. There are many helpful figures and tables throughout the book. The standard probability distributions are tabulated at the back of the book, where the reader will also find a bibliography of over two hundred references. There are sections involving hierarchical models, and mixture distributions, inequalities and identities which are absent in most available textbooks at this level. There are, however, a few sections which are presented at a higher level and could be omitted. The subsection on Bayesian tests might have been better presented. The concept of Bayes factor and some arguments against classical p-values should have been mentioned in this subsection. Overall the textbook is very well written, well motivated and easy to read. It is well suited for its intended audience as a solid introduction to theoretical statistics.
Reviewer: Dey, Dipak K. [form MathSciNet]