||New Reviews| |Software Methodologies| |Popular Science| |AI/Machine Learning| |Programming| |Java| |Linux/Open Source| |XML| |Software Tools| |Other| |Web| |Tutorials| |All By Date| |All By Title| |Resources| |About||
Keywords: Statistics, data analysis
Title: Intro Stats
Author: De Veaux and Velleman
Publisher: Addison Wesley
Verdict: A superb introduction to the subject
There are some people, or so it is said, who find books on statistics boring. Hard to believe but there it is. Here at TechBookReport we don't take such scurrilous rumours seriously. There are, unfortunately a number of authors who subscribe to this belief, and respond to it by writing 'the fun guide to multivariate statistics' or 'data analysis for groovy kids'. Even more unfortunately there are publishers out there who encourage this by publishing such books, knowing full well that the patronising nonsense within is neither fun, interesting or of much educational value. Thankfully 'Intro Stats' exists to show that it is possible to write, and publish, books on statistics which are interesting, engaging, unpatronising and which pack a good educational punch without getting bogged down in arcane mathematical proofs, heavy weight notation or dense formulae that frightens the horses.
This is an introductory statistics text, (the clue is in the title), which stands head and shoulders above most of the competition. The exposition is always clear and is aided by good design, with effective use of graphics and colour. The worked examples are exactly that, with a step by step approach that doesn't spoon-feed the reader but neither does it leave the reader behind by missing crucial steps. This step-by-step approach is very effective, and it greatly assists the authors in their aim to help the reader understand what is going on.
There is an emphasis on thinking things through, showing what the steps are interpreting the results that come out of the other side. This think, show and tell process is repeated in every chapter, and it helps instil a conceptual understanding that is essential for the would-be user and producer of statistics. Each chapter also includes a 'what can go wrong' section, which flags the pitfalls that can snare the unwary. Finally, each chapter includes a key concepts section that lists the concepts and gives a quick definition. This is followed by extensive sets of exercises.
Furthermore, each chapter includes notes for computer users detailing how the statistical technique that has just been explored can be implemented using a variety of software packages, including Data Desk, Excel, Minitab and others. It's worth noting the number of gotchas, caveats and general warnings when it comes to doing any kind of statistical work with Excel …
In terms of the material that is covered, the book starts with no assumptions about prior knowledge. Organised in six parts, it starts with an introduction to data, ways of displaying data, distributions and the standard deviation and then moves through relationships between variables (association and correlation through to regression), data gathering (randomness, sample surveys etc), randomness and probability (from intro probability to an introduction to Bayesian analysis) and on through to inference for related variables. The are even two final chapters on the accompanying CD (analysis of variance and an introduction to multiple regression).
The treatment of topics is of a uniformly high standard, and the text manages to be interesting and accessible without hint of condescension. It is in all respects a high quality product, from the packaging and design to the quality of illustrations.
If you are on a statistics course at college and this is your recommended text then count yourself lucky, this is one of the best. On the other hand if you're studying on your own, or you've been told to use another book then this is definitely a book that you need to look at.
There are no quibbles - this one gets the highest recommendation.