Customer Reviews


2 Reviews
5 star:    (0)
4 star:
 (2)
3 star:    (0)
2 star:    (0)
1 star:    (0)
 
 
 
 
 
Average Customer Review
Share your thoughts with other customers
Create your own review
 
 
Most Helpful First | Newest First

13 of 13 people found the following review helpful
4.0 out of 5 stars Bring back effect sizes, 14 Mar 2008
By 
Coert Visser "solutionfocusedchange.com" (Driebergen Netherlands) - See all my reviews
(REAL NAME)   
This review is from: The Cult of Statistical Significance: How the Standard Error Costs Us Jobs, Justice, and Lives (Economics, Cognition & Society) (Paperback)
This book shows how many scientific disciplines rely way too much on the concept of statistical significance. I have read the book and I find it convincing. The authors show how the focus on statistical significance has taken away attention for 'real' significance. In other words: the focus on statistical significance often means that researchers fail to ask whether their findings matter. In statistics, a result is called statistically significant if it is unlikely to have occurred by chance. So testing for statistical significance is asking the question how likely it is that an effect exists. It does not answer at all how strong and important this effect is. And this latter question about the effect size is much more important from a scientific and a practical perspective. Statistical significance does not imply an effect is important, lack of statistical significance does not mean an effect is not important. Mind you the book is NOT a plea against quantitative research nor statistical analysis. On the contrary. It is a plea for doing it and doing it right by bringing back focus on effect sizes in social science.
Help other customers find the most helpful reviews 
Was this review helpful to you? Yes No


2 of 4 people found the following review helpful
4.0 out of 5 stars Pulls It's Punches, But Still Causes Some Black Eyes, 9 Jan 2011
By 
Paul Woodfine (London, England) - See all my reviews
(REAL NAME)   
This review is from: The Cult of Statistical Significance: How the Standard Error Costs Us Jobs, Justice, and Lives (Economics, Cognition & Society) (Paperback)
A relationship between two variables is statistically significant if there is a low probability (usually less than five per cent) of it happening by chance. What the statistics textbooks don't tell you is that a relationship can be statistically significant but practically useless, and also that if the sample size is large enough, almost all the relationships you find will be significant. The same goes for statistical testing. This is one of the things this book will tell you. Another is, and not being a reader of statistical journals I was amazed to find, that most of the articles don't publish the magnitude of the relationships they discuss, only the significance level. What you really want to know, which is how much one variable affects another, usually is not published.

The book is the result of exhaustive scholarly research by the authors. There's a frank portrayal of Fisher and his school, and how the the cult got started, and a contrasting portrayal of their hero Gossett, who was a commercial practitioner, not an academic. The few side comments about how the insiders ignore most "statistical research" because they know it's meaningless, but don't say anything because people have to make a living, only whet my appetite for more. We know academics can be petty, but there's a faint whiff of actual intellectual corruption here. It's here that the authors pull their punches, because they have to work in academia. A journalist would not have been so restrained. What's missing, for me, is an examination of why apparently intelligent and sincere men and women should take part in such questionable practices. You will find the story about a survey of the effects of welfare subsidies (in the USA) especially suspicious: it found that the subsidies had a statistically significant effect for white middle-class women, but a "statistically insignificant" effect of half the size for poor black women. Well, gosh, what a surprise that study was taken seriously by the white middle-class people who administer welfare programs.

If you are interested in the application and history of statistics, this is one of the few books whose authors have not drunk the kool-aid, and so well worth reading. Oh, and that five per cent? Totally arbitrary. No connection with economic benefit at all.
Help other customers find the most helpful reviews 
Was this review helpful to you? Yes No


Most Helpful First | Newest First

This product

Only search this product's reviews