The Earth Is Round (p < .05) by Jacob Cohen, is a pretty entertaining read. Makes me wish I knew more about stats. It does contain the best snappy intuitive example of what happens if you get Bayes rule wrong, though. I'm used to hearing about tests for uncommon diseases (and he's got one of those too) but I love this false syllogism, for it's so obviously wrong:

A randomly chosen American is probably not a member of congress.
This person is a member of congress.
Therefore, this person is probably not American.