"Statistics is hard."

[bindeweede]

Quite a few years ago, on the old UKS forum, I asked if anyone could recommend a book on probability/statistics, as it was one of a number of topics I didn't understand. Someone recommended a book which I bought, but was unable to get beyond the first 30 pages or so. I don't have the necessary sort of mathematical/logical mind, it seems. The book went to a charity shop, and I have no idea whether they managed to sell it.

Harriet Hall has recommended a fairly short book - "Statistics Done Wrong: The Woefully Complete Guide."

This book is well written, short (129 pages), enjoyable to read, and easy to understand. It is well-organized, divided conveniently into short chapters, and is enhanced by the examples of research done wrong that illustrate each of its points. It covers the subject thoroughly yet concisely, and provides copious references for readers who want to know more. Rather than a guide to statistics, it is really more of a guide to critical thinking about pitfalls in the use of statistics.

I might well give it a try, but without very much optimism. :(

https://www.sciencebasedmedicine.org/st ... more-43022

(Could it be that those who understand statistics don't understand how those who don't understand statistics don't understand statistics?)

[Tony.Williams]

I have a couple of guides to statistics for non-mathematicians by John Allen Paulos: Innumeracy and Beyond Numeracy, published c. 25 years ago. They came highly recommended and were said to be best-sellers. As far as I can recall, I thought they were very good (well, I certainly bought the second one after reading the first, so I must have been impressed).

[Matt]

(Could it be that those who understand statistics don't understand how those who don't understand statistics don't understand statistics?)

I think you may be onto something there. Kind of like a corollary to the Dunning Kruger effect. In fact as I attempted to look up an appropriate phrasing I see the the wiki on Dunning-Kruger states

Their research also suggests corollaries: highly skilled individuals may underestimate their relative competence and may erroneously assume that tasks which are easy for them are also easy for others.

[AlJohnston]

Naked Statistics by Charles Whelan is pretty good.

I also enjoyed Jordan Ellenberg's How not to be Wrong

[bindeweede]

Naked Statistics by Charles Whelan is pretty good.

I also enjoyed Jordan Ellenberg's How not to be Wrong

Welcome, Al. After all this time, I'm just at the end of chapter two of the book I mentioned. But I will persevere.