This translation from the German by Luise Lange is superbly done. The book can be appreciated by high school level students who have an interest in math. I plan to use some of the examples on my web site which will employ math 101 and Visual Basic programming techniques....Leo JL...programmer at large

This is an excellent guidebook to path analysis and structural equations for biologists. The text is very readable (and even amusing in spots). There is interesting background on the development of path analysis and SEM, as well as thoughtful explanations of how these analyses can link hypotheses of causality to probability theory. New techniques for model testing are introduced that may add additional utility to the statistical method. I found it to be a thoughtful and thorough introduction to a potentially powerful new technique in biology and ecology.

For those wishing to upgrade their grasp of chaos theory, dynamics, nonlinear data analysis, with an introduction to related aspects of complexity including fractals and complex systems, this is the best book I have yet seen, and supplements the excellet visual dynamics books by Ralph Abraham. It arose from the upper level course taught by Sprott at the University of Wisconsin. The book is well supported by his website, which will always keep the book updated. It is nicely hands-on with lots of exercises and a programming project with each chapter. For those impatient to write programs, having a program like Berkeley Madonna to solve systems equations is handy for exploring some of the example systems. It has three excellent appendices, one a catalog of 62 dynamical systems, another useful mathematical formulas, and the last a compilation of useful journals. I found it incredibly comprehensive covering all aspects of the many subjects. And exceptionally clear, updating any necessary mathematics with clear explanations...

This is one of my favorite maths books. My interest in it is not so much for the discussion of chaotic systems, but more for that on stochastically perturbed systems. As far as this topic goes, this is the best book I've found in the field by far. The treatment is careful and self-contained, and the proofs are clear throughout. Lots of intuition is given with each result.

As a caveat, note that the approach is based on analysis in general and functional analysis in particular. If you prefer probabilistic arguments look somewhere else.

This book comes out with much anticipation from two of the world-renowned experts on nonlinear time series. Indeed, the once superhot chaos theory in physics and math in the 80s was only introduced to statistics by Howell Tong in his 1990 book on nonlinear time series, Tong and R. L. Smith's 1992 RSS Chaos Day workshop and subsequent JRSS B special issue on chaos and L M Berliner and others's 1992 review articles in Statistical Science. Now 10 years after, what has achieved in between and what has not materialized as once seemed so promising? There are several PhD theses written in this area and there are continuing applications of chaos theory in science, from physics, mechanics, atmospheric sciences to biomedical and physiological data analysis. We can safely say that chaos theory is probably just another area or another tool that one can use to understand or interprete apparent randomness in simulations or in observed data. With purely stochastic tools that are dominant in modeling high-dimenional and un-parameterizable processes, chaos theory provides the crucial link between deterministic and computer modeling, and uncertainty in observed output and model simulations. Maybe with the ever closer collaboration between statisticians, mathematicians, and physical scientists in understanding and using the most daunting PDE and large scale models or computer models, chaos theory may finally come to be appreiated more by statisticians, who have traditionally been over-concerned with modeling noise, while overlooking modeling the overall deterministic patterns and structures in data.

Finally, some words about the book itself. I think it is a fairly comprehensive survey on the statistical work in the last decade, though understandably it is biased toward the authors' own research and collaborators' work. I think in order for it to be used as a textbook, it needs to be supplemented by a more balanced account of other aspects of chaos theory, such as geometrical theory and dimension reduction techniques. For example, the review chapter of dimension theory by C. Cutler in a book edited by H. Tong himself in 1990 (published by World Scientific) and Michael Kirby's recent book: Geometric Data Analysis: An Empirical Approach to Dimensionality Reduction and the Study of Patterns. The significance of fractal geometry theory on multivariate data analysis and time series statespace when the vector may lie on an manifold or lower-dimensional intrinsic space has recently been demonstrated by Z.Q. Lu in Nonparametric Regression With Singular Design in J. of Multivariate Analysis 1999, vol. 70, pp.177-201. It appears that the potentials of chaos theory for motivating newer statistical techniques and developing new statistical theory to understand better deterministic systems and related data analysis remain to be explored. In conclusion, I warmly recomend this book to next generation students and time series lovers, and to scientists who might be wondering what statisticians are up to in this important area.

An excellent introduction to chaos for the mathematically inclined, this work offers a brief tour through the concepts and theorms behind the field of chaos and nonlinear dynamics. Having a college mathematical background is decidedly helpful in getting use out of it, but having a mathematical mindset is absolutely essential.

This is a good introduction to logic, inductive and, to a lesser extent, deductive. It probably serves better as a textbook than as an aid to individual learning, but under the proper conditions and with the proper reader, it could serve both. I liked it best when it was explaining the truth tables and the rules of the calculus of probability. Particularly interesting are the practical applications in the exercises, especially in cards and dice and, to a lesser extent, horse racing. The concepts of utility and belief need amplification because they come off too briefly in relation to their importance. No one who has mastered this book would ever have trouble calculating the exact value of a bet - a benefit of some importance to us gamblers. I have never seen or heard of the theory of marginal value applied to money. It certainly applies to other things, like water. Too little water makes water very valuable, enough is enough, and too much gives water a negative value (as in our current flooding in Texas). Skyrms is right about some aspects of money: Too little and it hurts. Don't believe me? Try walking around New York City on the weekend with only a dime in your pocket. A poor man would be a fool to risk $1000 on an even money bet. Because if he lost, it would hurt a lot. A rich man could lose that bet and not suffer at all. And of course, enough money is good. Therefore, money does have a relative value. Whether it has a marginal value (too much is bad) is debatable. Some things that might be corrected in the next addition: The answers to the exercises should have pages numbers for more easy reference. The cover is wrong in saying there are answers for every other problem. That is only partially true and in fact some exercises have no answers eg VIII 3 has no answers to any exercise. And Symes is wrong in assuming that evaluating all the evidence doesn't cost anything (page 154). It costs time and trouble. Whether it is worth it would depend on the situation.

Crowder has written an up-to-date text on an important problem in health science and medical research. The first good monograph on this subject was by David and Moeschberger in 1978 and no text devoted to this topic had been written until now. People get sick or die or hardware fails due to one of several possible causes. In the competing risks model these causes are all given probabilities of occurrence over time and "compete" to be the first to occur and thus cause the event.

The mathematics of competing risks is very much the same as the mathematics of survival analysis but instead of a single time to event curve there are many. For data analysis, one must be able to get data that includes not only the time of occurrence of the failure but also which of a list of possible causes the event is attributed to (the list of "competing" risks).

Crowder's text is introductory and reviews a lot of the basics of survival analysis and likelihood inference. Hazard functions and survival curves are introduced as are sub-survival curves and sub-hazard functions. The nonparametric Kaplan-Meier approach to survival analysis is presented as is the semiparametric Cox proportional hazards model. The important issue of parameter identifiability is given its proper place of importance.

The first seven chapters are written at an elementary to intermediate level that should be understandable to the undergraduate or graduate student taking this course. However, Chapter 8 deals with the modern and powerful counting process (martingale) approach to survival analysis and is more difficult to read. Chapter 8 has more of the flavor of an advanced probability topic and is suitable for graduate students who have taken that first advanced probability course.

This book is helping me a lot with my Ph.D. dissertation. It includes a lot of important results on hypercomplex analysis not usually found in the standard monographs on the subject (Brackx, Gürlebeck, Shapiro,...).

Its contents are: Clifford algebras, Dirac operators and Clifford analyticity, representations of Spin(V,Q), constant coefficient operators of Dirac type, Dirac operators and manifolds.

Presents motivation for each section and extensive references. A must-reading to become a speciallist in this area. Suitable for graduate students and researchers.

Please read the rest of my reviews (just click on my name above).

I should begin by admitting that I had the opportunity to review this little masterpiece in manuscript. Good then, it's even better now.

It's good because it informs the reader, in sober prose, how to determine what works and what doesn't in medical practice, and what's safe and what isn't. It's good because it reveals what can go wrong when anecdotes ("it worked for me!") substitute for sound research as the basis for clinical practice. And it's good because it shows how serious are the consequences of even subtle failures to observe protocols in designing and carrying out clinical trials.

It is reassuring to read of the care and precautions advocated for government-sponsored research; it is accordingly unsettling to contemplate the pressure that commercial interests (drug companies, for-profit hospitals, equipment manufacturers) might bring on researchers to cut a few corners.

After reading "Clinical Trials" I came to appreciate that case studies, longitudinal studies, and retrospective questionnaires, so frequently hyped in the press and on television, are no substitute for actual well-designed and well-executed experiments. Because you and I are different, certainly genetically and probably in other essential ways, what helps you may well harm me. Only the proper application of statistics in designing clinical trials and in analyzing data from them can distinguish what's generally valuable from what's useless (however plausible and authoritatively touted it may be). Although the authors had the good taste to reject the aphorism, usually attributed to a nameless statistician, that "if experimentation be the queen of science, then statistics stands as the guardian of the royal virtue", its pithiness may give the reader the crucial insight into why alternative modes of research are untrustworthy.

Some readers may feel disheartened to learn the truth that many, probably most, promising therapies prove, when adequately tested, worthless, and some may feel in some fuzzy way that to accept this reality is cruelly to deny hope to those who need it badly. On the contrary, this book makes it clear that to offer false hope is the ultimate cruelty, for without experimentation there can be no knowledge, and without knowledge there can be no real hope.

Notwithstanding the slightly technical nature of this book (yes, there IS a chapter with mathematics), I recommend it highly for the general reader who is interested in such topics as personal health care, alternative medicine, managed care cost containment, and the like. Buy a copy for yourself, and, if you feel philanthropic, you might consider donating a copy to your health care provider. The world would be better if doctors' waiting rooms (like hotel rooms with their Gideon Bibles) all had a copy of "Clinical Trials in Oncology" available for patients' perusal.