Invariant small sample confidence intervals for the difference of two success probabilities

Abstract
An algorithm is proposed for determining 100 × (1 − α)% small-sample confidence intervals for the difference δ≡ p1− p2 of two binomial success probabilities based on n1 and n2 trials, respectively. The interval covers the true δ with probability at least (1 − α) for all 0 < p1, p2 < 1; it is invariant with respect to relabeling of the two populations and with respect to interchanging the outcomes of success and failure intervals. Coverage and expected length comparisons are made with the small sample 100 × (1 − α)% tail intervals of Santner and Snell (1980). A FORTRAN program implementing the algorithm is available from the authors

This publication has 10 references indexed in Scilit: