Exact Confidence Limits for Population Proportions Based on the Negative Hypergeometric Probability Distribution

Abstract

An algorithm and FORTRAN 77 subroutine are presented to calculate exact confidence limits for the number of successes in a finite population, given a random sample drawn without replacement. The limits are calculated recursively from the negative hypergeometric probability distribution. The use of an arbitrary initial value in the recursion eliminates the computation of factorial expressions.