- Statistics Without Tears – A Primer for Non-Mathematicians
- by Derek Rowntree
- Charles Scribner’s Sons
- Copyright 1981
- 190 pages
Rating (for pages 1-126) – 7 out of 10
Sometimes in life, we have to face the facts – a relationship isn’t going to work out, we’re never going to play major-league baseball, all food that tastes good is bad for us, etc. Books are no different – sometimes reality intrudes.
Monday I had to accept that Derek Rowntree’s Statistics Without Tears just isn’t as good as I’d remembered it being. Don’t get me wrong, Tears is a good book. But it’s still a stats book that requires a lot of mental effort to understand. Also, Tears will work best as a supplement for use while studying stats in the traditional manner (i.e., studying the basic concepts and working a ton of problems); it does not replace the old methods.
Chapter 6 (pp. 102-126)
After that intro, it probably will come as no surprise to say that the material that I read Monday – Chapter 6 – has Rowntree taking his readers even deeper into the statistical weeds. He gets into a number of statistical topics including –
- testing to see if two measures come from the same population,
- Type I and II errors,
- estimating the standard error when conducting statistical tests, and
- Non-parametric tests
Lost in the Woods
A Spanish teacher I once knew described students who were completely clueless as being “lost in the woods.” I haven’t gotten completely lost (yet), but I wandered off the path a few times. Chapter 6 required me to do some hard thinking. At the end of the chapter, Rowntree concedes that “You’ve probably found this to be the most taxing chapter in the book so far… if you feel the need to skim through this chapter again before starting on the next, I shan’t be in the least surprised” (pp. 126-7).
I don’t want to be give the impression that I am wholly negative – I am not. Rowntree writes about statistics as well as any author I have read. His explanations are far superior to those in most stat textbooks. But, having said that, statistical concepts are difficult and even Rowntree cannot spare us some hard thinking.
