The N=1 analysis differs from a typical analysis of variance in that there is no within-cell error term. Thus interaction terms are used as estimates of error variance. If the interaction term in question represents a significant interaction, the F tests will be conservative. Tukey's test for nonadditivity will detect a common form of interaction. Listed in this paper is a computer program to calculate the N=1 analysis of variance and the necessary tests for nonadditivity. (Author)