Customer Reviews

Probability and Statistics (2nd Edition)

5 star:		(16)
4 star:		(2)
3 star:		(3)
2 star:		(4)
1 star:		(4)

 

 

This is an introductory book. It also fits in introductory level of Mathematical Statistics. The prerequisites are introductory calculus and linear algebra. Most theorems are proved in calculus style but there are some gIt can be shownsh that are not proved. So some readers may not be satisfied with the book, especially Math majors.

Logical steps are shown in detail; else logical gaps are contained within a level such that a first time reader can fill in the gap with a pencil and paper. Occasional mix with Bayesian perspective is also a feature. Answers to odd-numbered exercises are provided except ones that ask derivations and proofs. Exercises that require some tricks are provided with hints. In these respects, this textbook is suitable for self-study.

Upon completion of the entire material, I feel concepts are developed well up to Hypothesis testing Chapter 8 where the presentation of material reaches climax and its level of exposition is somewhat higher than other chapters. Thereafter, simple linear regression is treated in detail, but coverage and detail of materials seem to deteriorate from the following general regression section, nonparametrics and thereafter. Kolmogorov-Smirnov Tests section is treated nicely though. Anova section lacks in coverage. The new simulation chapter is presented more like a demonstration rather than an introduction.

I have never seen the previous 2nd edition (unfortunately Dr. Degroot is no longer with us), but according to the preface of this 3rd edition, Dr. Schervish describes 8 major changes from the previous edition. Notable are some material removed from the previous (likelihood principle, Gauss-Markov theorem, and stepwise regression), some added (lognormal distribution, quantiles, prediction and prediction intervals, improper priors, Bayes test, power functions, M-estimators, residual plots in linear models and Bayesian analysis of simple linear regression), more exercises and examples, special notes, introduction and summary to each section, and so on. I find the last in the list is somewhat disturbing, especially introduction parts that are often redundant with the very next paragraph. On the other hand, I find that special notes provide good insights.

I wish they included introduction to Statistical Decision theory, full coverage of regression analysis to be usable such as diagnosis, transformation and variable selection, coverage of Multivariate Normal distribution, more coverage and depth in nonparametrics and simulation, and lists of recommended readings for further study at the end of each section with comments.

There are a noticeable number of typos as of this first printing I have. I sent suggestions for typos and was impressed that Dr. Schervish updated errata list within a few days at his homepage. I wish all authors were like him being responsible.

After having used this book in a graduate level probability/statistics course and having the opportunity to poll students who took that class over the past 3 years, I found out that the probability of getting a good grade, and achieving understanding with DeGroot, was small.

To my joy, the university now uses Fredrick Solomon's book entitled "Probability and Stochastic Processes" for their 4000 level course.

After reading Solomon's book, I found myself getting unconfused and after having studied Jim Pitman's Probability book and Freedman's Statistic's book, I can now get into DeGroot's book. I am also going to get Feller's book, volume 1. What I needed, and DeGroot didn't offer, was a better feeling of "number sense" or what I think of as the "physics of numbers." I also wanted to know about the connections between things (concept maps) and DeGroot didn't do this, initially, for me.

I agree with the other reviewers that DeGroot's book is interesting but I don't believe that DeGroot sequenced the information well or had the desire to bring out a lot of the hidden details. Of course, after I read the other books I mentioned, I am beginning to see how wonderful DeGroot is for the advanced learner because he puts things together in interesting ways. However, to get to that level of appreciation, and see the "deeper connections," I really needed a stronger foundation on which I could appreciate DeGroot's heavy dose of algebra and matter of fact presentation.

In short, I found this book to be "the exam," but not "the course."

As a social science student (economics), statistics are crucial in a large array of topics of interest. During my studies, I have bought many probabilities and statistical manuals in order to understand the underlying theory I study (econometrics). So far, no one is better than this one (Mendelhall, Monfort among others). As someone said, probability is not an easy topic; sometimes it's pretty hard to understand particularly abstract concepts. Nevertheless, the author teaches you through an impressive quantity of examples. You don't need to be a genius in math's to understand him, because he explains pretty well. The equations are all understandable and the author's doesn't use I high level of sophistication to present complex problems. The content is pretty impressive; besides the classical probability theory (basic concepts, conditional probability, random variables, expectation...), there is an extensive section dealing with estimation techniques (maximum of likelihood, OLS, and Bayesian estimators) there is a chapter dealing with statistical tests and another with non-parametrical methods. The latter is somehow oldie and there are no explanations of the kernel density estimation or kernel regression. The other objection I can raise is that there are no explanations neither of sigma-algebras, a concept used in advanced probability. Of course, it's an introductory book, thus such drawbacks are understandable. This book should be in your library.

This was my first stats book in college. I really liked it a lot, and maybe it is why it helped me appreciate stats. This book is very versatile and somehow explains sophisticated concepts with the greatest of ease. It has great examples, and I learn better with those. This book was used not only in my undergrad courses (Stats I and II, back mid-'70's) but also in my MBA curriculum (as a later edition) 10 years later. I have yet to run into a better book for someone studying stats for the first time. Also good at probability, which is one of the most obtuse, counter-intuitive subjects for humans to understand.

This book is very clear and readable, although its subject may be difficult. It has been a classical for a long time - first edition in 1975 - and it is extremelly well written; and, indeed, very appropriated for beginners who have taken two semester of calculus and wish to learn Statistics.

It presents all classical statistical results, formally and intuitively. The exercises have different degree of difficulty, and they are all very good - the answer, not the solution, of the even exercises are in the end of the book.

In my undergraduate, I used this book to study. So I think the undergraduate instructors on this subject should consider it a good option to be adopted as a textbook.

This new editon mantains the features that have made it a classical for a long time:

- Clearly written;
- Tough subjects are made understandable even for beginners;
- Classical results are presented rigorously after a bunch of examples;
- Many exercises, well posed, whose solutions are found in the end of the book (just even exercises).

This books has been long without a revision and we can see easily that it is much better. The main improvement is the computational treatment of Statistics in terms of theory and exercises. And, of course, it is visually more pleasant.

You may think this is little, though. But, a classical is so well done that there is not much more to do. This is the case. So the second author adds what was difficult when DeGroot first wrote it (computational stuff, as I said) and suppress what is out of fashion or has been overcome.

I think it is still the best option to start out to learn Statistics.

First all, everyone wishing to learn probability comes from different background, math level, and motivation. There is no book that suits all. Recently I needed to know something about moment generating functions. With all my advanced engineering background though, I find it difficult to get into probability.

So I bought the following supposedly introductory texts: Ross, DeGroot, Stirzaker, Bersekas & Tsitsiklis. To me, Ross seems like a review lesson to cram for finals; it's choke full of examples but fairly spare in exposition. DeGroot is the opposite, long on descriptions but short on examples; by the time it finishes describing the problem, you have forgotten how to solve it. Probability is set up more as a prelude to statistics in the second half of the book. Stirzaker calls his book "elementary" the way Sherlock Holmes dismissed a case after slogging all night through the English bogs. It is more for the well-drilled boys from elite British "public" (private actually) schools. Bersekas comes closest to what I look for in a text, straightforward in prose with a judicious selection of examples to explain theory.

For beginners, the best approach I found, in the end, was to go the local community college and buy the text used for Finite Math. Usually, there are 3 to 4 chapters that introduce probability.

Such a text is aimed an audience from wider academic and language backgrounds, as community colleges are mandated to do. Therefore, probability is taught in simple, plain-spoken language crafted through multiple editions. One such is Finite Math, by Karl J. Smith; however, many others like it will do. For self-study, one might start in the chapter on probability to understand the author's approach, then go back a chapter or two to pick up the permutation and combinatorial math needed to calculate probability. Another alternative is just to enroll in a Finite Math course at a community college. Generally, such a course stops at Markov's chain which is enough to get you jump started in probability.

In any case, a good Finite Math text gives plenty of examples with clear, succinct, and layman-like explanation to help you tackle Ross' book or supplement any other at a higher level. If you plan to apply probability to your work, then shop around for another text after you get the basics. The thicker tomes delve more into theory which is good because real life problems are seldom like the examples given. However you can't go wrong by planting your feet solidly on a good Finite Math text first

I used to hate statistics, but this book is pretty clear and concise, and gets the idea across very quickly and easily. The exercise questions were of reasonable difficulty, and are put forth in a clear manner, unlike other books which present the questions in round-about manner. The examples tend to follow on or build upon from the earlier chapters, so it is best to tackle the book in the order as prescribed by the chapters.

Probably one of the most elegantly written book that I have ever read. I am not sure probability and statistics can be introduced with a greater degree of clarity while mainitaining mathematical rigor. Absolutely beautiful flow and crisp results.

An earlier edition of this book was the text when I took my first course in probability and statistics. Now that I teach math and computer science at a small college I am always on the lookout for a new text and so I examined this book within that context. The coverage is at a high mathematical level; there are many theorems with proof. However, there are also many worked examples that demonstrate how the theorems are applied. The quality of the exposition is such that it is very readable for those who have gone through a three-semester calculus sequence.
The chapters are:

*) Introduction to probability
*) Conditional probability
*) Random variables and distributions
*) Expectation
*) Special distributions
*) Estimation
*) Sampling distributions of estimators
*) Testing hypotheses
*) Categorical data and nonparamentric methods
*) Linear statistical models
*) Simulation

A large set of problems appears at the end of each chapter and solutions to the odd-numbered ones are included in an appendix.
The high level of readability that I appreciated so much when I learned from an earlier edition has been maintained through this one. I can strongly recommend this book as a text for upper level courses in probability and statistics.