Stein's lemma

From Wikipedia, the free encyclopedia

Stein's lemma, named in honor of Charles Stein, is a theorem of probability theory that is of interest primarily because of its application to statistical inference — in particular, its application to James-Stein estimation and empirical Bayes methods.

[edit] Statement of the lemma

Suppose X is a normally distributed random variable with expectation μ and variance σ². Further suppose g is a function for which the two expectations E( g(X) (X − μ) ) and E( g ′(X) ) both exist (the existence of the expectation of any random variable is equivalent to the finiteness of the expectation of its absolute value). Then

E(g(X)(X − μ)) = σ²E(g'(X)).

In order to prove this lemma, recall that the probability density function for the normal distribution with expectation 0 and variance 1 is

and that for a normal distribution with expectation μ and variance σ² is

Then use integration by parts.