The first chapter of Howard Wainer’s book Picturing the Uncertain World, entitled “The Most Dangerous Equation”, is available from Princeton. (The equation in question is the fact that the standard deviation of the sampling distribution is the standard deviation of the population divided by the square root of sample size.
John Cook wrote sleeper theorems, theorems that one only comes to understand the importance of long after learning them; his list includes Bayes’ theorem and Jensen’s inequality.
J. Michael Steele is teaching Statistics 530 (first-semester graduate measure-theoretic probability) at Penn this semester. (I’ve taken classes from him, and I took this class, but he wasn’t teaching it.) Embedded in his course web page is an interesting aside on how mathematics gets done:
GRaVy: This stands for “Generalizations”, “Refinements” and “Variations” and this one word represents the way that 80% of day-to-day mathematics (and mathematical science, including statistics and computer science) gets created. The paradigm needs no modification in mathematical statistics, and the story for applied statistics requires only small modification.
This also includes an implicit list of “genres” of mathematical papers (which is incompletely written; I assume that this picks up on something said in class): the “Generalizations”, “Refinements” and “Variations” above, “Greenfield Projects”, “P+Q=R”, “synthesis” or “survey”, and the “Pollution Piece” (which pollutes the literature). What other genres are there?