It's not easy to find good books about simulation techniques for experimental phenomena for general purpose: one must rely on area-specific texts (computational physics, computational biology, optimal control, etc.), that often lack important topics, so in introductory level as in specific procedures and possible generalizations. This book has it all: practically self-contained for those with basic notions about calculus (its chapter about probability and statistics, although brief, is enough to follow the rest of the book), it is centered on learning how to do simulation in real-life situations. His depth and detail in treating random number generation, for arbitrary probability distributions in discrete or continuous case, is matchless (it occupies a third of the book). Another differential is the thorough treatment of Monte Carlo methods, Markov models, as well as topics concerning model construction and analysis, and error estimations. All this with profuse examples from biology and statistics, and lots of exercises at the end of each chapter (many of them with commented resolutions at the end of the book), as well as a huge bibliography and a guide to FORTRAN IMSL and NAG routines for use in several simulation techniques (random number generators, Markov chains, etc.). I only regret that the few code listings are only in BASIC and MINITAB. As a physicist, I'd like to see some of these codes in Fortran or C (even because it would be coherent with the routines guide); but I can't ask too much, because people at business, engineering and biology may not agree with me in the programming language choice. Anyway, it's a remarkable and very useful book. I can't get rid of it in my work in Monte Carlo simulation. If you are interested on or work with statistical simulation in any area of science or technology, you'll certainly do well in acquiring a copy: it won't disappoint you!
