What is a p-value anyway?
By Andrew Vickers.
Another saunter around statistics, this book is a humorous approach to understanding many statistical techniques used (both correctly and incorrectly) in the sciences. And Andrew is funny, with a good blend of story and instruction on what the hell statistics is about and how the most common techniques are applied. Even though it’s very basic, for instance he never goes into how to calculate a p-value, the conceptual and intuitive explanations for simple techniques was incredibly useful. Even the very beginning, looking at the differences between mean/standard deviations and median/quartiles was interesting.
Major things I remember: it doesn’t make sense to calculate multiple p-values for a single experiment and definitely never compare them. p-values is an indication of the likelihood that your null hypothesis is true, so calculating more than one implies you’re testing more than one null hypothesis. In addition, you just can’t compare them. I doesn’t make any sense. Also, p-values can be skewed by sample size, so make sure you understand your data before calculating a p-value otherwise it might give you a deceptive result.
He got a little more technical towards the end, but not as much as I’d like. He started talking about Wilcoxon values and ANOVA but didn’t really go into what they were. I think it would have been better if he got more technical as the book went on, where at the end the level was maybe college math. That way people could bow out of the book when the math got too involved, or continue reading but skip the mathematical explanations.
Still, a fun and easy read and probably one everyone should be reading in high school to ensure everyone is statistically literate.