Analysis of data from our laboratory and that of two National Cancer Institute contractor laboratories indicate the random variation in the results of the mouse lymphoma L5178Y cell TK locus mutation assay can be adequately described by a lognormal distribution. This indicates that transformation of mutant frequencies to logarithms enables one to properly use well-known statistical techniques such as analysis of variance, regression analysis, and Student's t-test for the interpretation of data from this assay. The consistency of the lognormal distribution among laboratories is demonstrated. Three examples which illustrate the mechanics and interpretation of the proposed methodology are included. It is concluded that the method is effective in identifying weak mutagens as well as enabling the user to compute the uncertainty associated with an observed increase in mutagenic activity.