||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: Statistics For People Who (Think They) Hate Statistics
Author: Neil J. Salkind
Publisher: Sage Publishing
There are thousands of students all over the world for whom the study of statistics is an essential but unejoyable chore. A bit like going to the dentist only not as expensive, though possibly the dentist is preferable because the pain disappears in a few hours while a stats course lasts a whole semester (or more). For such students there are dozens of books on stats, probability and research methods which are aimed at providing help and support in a friendly and approachable manner. Neil Salkind's book is one of those, and note the hopeful implication in the title - people who think they statistics. Once they get to grips with the subject then they'll come to love it. It's an optimistic thought …
Well, for the nervous reader, there's a lot to commend in this book. For starters it's very much a hands-on book, with step-by-step instructions, writing that is clear and to the point, plenty of tips and pointers on things to remember. The book also makes good use of SPSS, again helping the student work through examples and get to grips with the software (and more importantly helping to explain the output that SPSS delivers). There's not a mathematical proof or derivation in sight, it's not a maths book in that sense, it's a book that uses maths rather than teaches it.
The range of topics that are covered is ideally suited to research methods courses in the social sciences. It includes graphical representations of data, correlations, probability distributions, tests of significance, introductions to regression, basic inference, analysis of variance and so on. While the book is very clear on the mechanics of performing the calculations, it is also very good at explaining the meaning of the results. Knowing how to compute a correlation coefficient is not much use if you have no idea what it means. Salkind takes care to make sure that everything makes sense in language that the non-mathematical reader can easily grasp.
The quality of the writing has already been mentioned. For example it includes a very handy flow chart to allow the reader to work out what kind of test of significance to select for their data. There are data sets that can be downloaded and used with the exercises that finish each chapter. There are also answers to the exercises, a real boon for those who want to practice what they've learned.
In all then, there's lots to commend this book. It's readable, helpful, humorous and works to gently the guide the reader through an unfamiliar new territory. The aim is to give the reader both the knowledge and the confidence to think about statistics and how it's used in the real world.