A stronger form of the Chebyshev inequality. Let X1, X2,…, Xn be independent random variables with finite expected values and variances. Define the partial sum Sk byThe inequality states that, for all positive values of ɛ,where, for each k, μk and σk2 are, respectively, the expected value and variance of Sk. See also Bernstein inequality; Hölder inequality; Markov inequality; Minkowski inequality.