Advisor: Jon Wellner
Abstract: We discuss a method for obtaining finite sample Gaussian bounds for the tail of the hypergeometric distribution. The method is based on TusnÃ¡dy's approach (1975) to bounding the tail of symmetric binomial random variables. In this talk, we review TusnÃ¡dy's result, and discuss how it can be adapted to and extended in the hypergeometric case. We discuss how these bounds, combined with bounds for the hypergeometric tail that incorporate information about the population variance into the bound, imply an improvement to Serfling's inequality (1974) when the hypergeometric parameters are constrained.