Customer Reviews

Statistical Models: Theory and Practice

5 star:		(5)
4 star:		(1)
3 star:		(1)
2 star:		(1)
1 star:		(0)

 

 

The Best Statistics Book I've Seen
I spent my life focusing on the errors of statistics and how they sometimes fail us in real life, because of the misinterpretation of what the techniques can do for you. This book is outstanding in the following two aspects: 1) It is of immense clarity, embedding everything in real situations, 2) It uses the real-life situation to critique the statistical model and show you the limit of statistic. For instance, he shows a few anecdotes here and there to illustrate how correlation between two variables might not mean anything causal, or how asymptotic properties may not be relevant in real life.
This is the first statistics book I've seen that cares about presenting statistics as a tool to GET TO THE TRUTH.
Please buy it.

Nassim Nicholas Taleb

This book is a very well-written, but ultimately fairly conventional textbook on linear models in statistics. It offers a very clear elementary introduction to the mathematics of the material, with an emphasis on both applications and rigor. It is to-the-point and does not cover very much material, instead choosing to cover material thoroughly and demonstrate the application of the material in practical situations.

I have heard this book described as "skeptical". It is not unduly skeptical; the author is just being the way every statistician ought to be. Any statistician who is not "skeptical" in this sense is accepting sloppy work.

The writing style in this book is very clear. Freedman is an outstanding writer! The book makes use of a decent amount of linear algebra and other mathematical notation that can be difficult for people to get through, but Freedman provides a very gentle introduction to the notation both through the text and through exercises (broken into small pieces, with a smooth gradient of difficulty). If you take your time and work through the book, you will not find it difficult to read.

Still, this book is not the be-all and end-all of texts on statistical models. It is particularly lacking on philosophical depth when it comes to the mathematical theory. This book describes techniques that are common practice and teaches you how to use them properly and evaluate them critically. It does not probe very deeply into how or why these techniques were developed. It does not encourage the reader to question the techniques themselves or to create new techniques or new theory. In my opinion, this is a shortcoming worth mentioning.

Also, there are a wide variety of topics that this book seems to ignore. By ignore, I not only mean that it does not cover them but that it is written almost as if these subjects do not exist. These subjects include, among others, causal inference, Bayesian statistics, and decision theory. For example, the book accepts squared error loss as a given, and other options, such as mean absolute error loss leading to quantile regression, are not even mentioned. I think the author should at least acknowledge these other perspectives and branches of statistics, briefly discuss how they relate to the material covered in the book, and point the reader to other texts to cover such material.

Is this a good book? I see it on many peoples' shelves. Personally, I found it immensely useful for learning linear regression properly. It is outstanding for self-study and would make a good textbook as well. But it does not stand on its own, even if all one wants to learn is regression. For what it is, this book is simply amazing; know its limitations, however, before buying it.

The formal reviews say this book is very well written. That is an understatement. Freedman uses plain English and interesting examples to explain the concepts behind the statistical jargon. This book is certainly good for those who will go on to advanced statistics and those who can read mathematical notation more easily than words. For those of us who need to apply the results of statistical studies but who do not wish to gain graduate degrees in statistics, Freedman gives us the background to understand studies we have to use, an understanding of whether regression is an appropriate model for specific situations, and the tools to ensure we are making appropriate comparisons. This book IS well written because it leads to understanding concepts rather than mechanical memorization.

The late Professor David A. Freedman possessed the rare skill of being at the top of his profession in both theoretical and applied statistics. His introductory text with the simple title "Statistics" has been praised as one of the best ever written. On the other side he could write very deep mathematical books as was demonstrated in his trilogy on Markov processes and diffusions. In the real world he contributed to the application of critical thinking about the pros and cons of statistical models and was steadfast in his position against the adjustment of the decennial US Census even though most prominent statisticians stood on the other side. He did consulting which grounded him into real applications particularly in Econometrics. As a Berkeley professor he collaborated with many of the top theoretical statisticians in the world. Many of which were at Berkeley or Stanford.

I concur with the enthusiasm for this book that is shown by the other 4 customer reviews. Persi Diaconis from Stanford was a long-time collaborator with Freedman and the late Erich Lehmann long-time Berkeley colleague. I think the praise for this book shown by them is far more important to hear that some of the nice things I might say.

Diaconis: "At last, a second course in statistics that is serious, correct, and interesting. The book teaches regression, causal mdoeling, maximum likelihood, and the bootstrap. Everyone who analyzes real data should read this book."

Lehmann: "This book is outstanding for clarity of its thought and writng. It prepares readers for a critical assessment of the technical literature in the social and health sciences, and it provides a welcome antidote to the standard formulaic approach to statistics."

Lehmann was a great writer himself and in addition to his research contributions to parametric and nonparametric statistics he presented and extended the Neyman-Pearson theory of hypothesis testing in his first book "Testing Statistical Hypotheses" and its subsequent revisions. With that in mind Lehmann's comments about Freedman's clarity of exposition should be taken very seriously.

In addition to covering applications and hitting the mostimportant topics in applied statistics in the eight chapters Freedman reproduces completely articles that applied statistics in the sociology, economics and political science journals. he devotes a complete chapter (Chapter 7) to bootstrap methods form estimating bias and standard errors. As an author of a book on the bootstrap I know how difficult it is to explain the bootstrap in a technically accurate way without pouring on the asymptotic theory that goes away from intuition. Freedman, who was a major contributor to the asymptotic theory of the bootstrap and its application in regression and simultaneous equation models that are so often used in econometrics, uses this knowledge and his gift of writing to present this in a way that I will want to learn to emulate.

Whether we know it or not, assertions about causality based on regression models from the social and health fields guide decisionmakers to make or break policies that affect all of us. Students learn the mechanics of how to do a regression model without paying much attention to the assumptions behind the model and when it is appropriate to claim causality. The rest of us use the results without questioning whether the assumptions are justified in a particular case.

You don't have to be a hardcore mathematician to understand David Freedman's explanations about the "how" of statistical modelling, and most importantly, the "why," and the "when" of modelling. Dr. Freedman's writing style is direct and he provides many useful examples of when the techniques are appropriate. He provides exercises followed by detailed explanations of the correct answers. This book is certainly of great value to students but I also recommend it to those who use the causality statements from the models to make decisions.

If you are looking to a statistic book directly connected with the reality of using statistic in the day-by-day life more than just showing artificial exercises and, by consequence, not only learning the tools but also discovering pitfalls (common and less common) in building models and in making deductions from them, this is your book.

I've done a bit of least squares in basic statistics, but I wanted to learn more. This book got such great reviews that I ordered it. I read the first five chapters. I hate to speak ill of the dead, but really, this is a terrible book. A lot of the book and what the author is trying to teach is embedded in exercises and problems. Unfortunately, the author does not provide answers to these. So the reader without the solutions is forced to skip a lot of material.

One of the core features of the book in theory is the discussion of least squares. I found this obscure, at best. The discussion of least squares is in terms of linear algebra, which is great. But the jump is rapid and it is difficult to tie the description back to application. Despite all of the proofs I wanted more detail on the derivation for the least squares equations, but I didn't find it. At least not in a for I could understand.

In short, this book is not at all a book for self-study. I suspect that few in the social sciences and even Biology would find this text useful. It's just too obscure. What a disappointment!

I'm returning mine to Amazon and looking for a better book on least squares and multiple regression.

It seems the author is on a quest to document statistical models pitfalls and express his frustrations against some of the misconceptions of statistical analysis. Certainly this is the most complete statistics book I have seen in terms of mathematical proofs, but the title "Theory and Practice" seemed to imply a text oriented towards applications. There are a number of classic case studies presented, but statistical analysis has evolved since then and I for one knew that an imperfect tool it is, not a mean to predict the future or express causality under every circumstance.

In short buy this book if you are in an academic path and want good mathematical foundations on linear regressions and probit models. You will still need assistance though because formula explanations are reduced to a bare minimum.