Investigations of size variation in fossil and archaeological skeletal assemblages may be complicated by incomplete skeletons, biased representation of sexes, and the lack of morphological features that identify sex. In order to refine our ability to evaluate size variation, we test the accuracy of three methods that are currently used to estimate size differences in unsexed (pooled) samples: the means method, the median method, and a newly applied technique, the method of moments. Using body mass data from 42 primate species, we calculated actual levels of sexual dimorphism for each species and compared these values to estimates produced by each method. Multivariate regression was used to examine the effects of sample distribution characteristics, including sample size, kurtosis, skewness, sample variance, sex ratio, and intrasexual variance on the performance of the methods. None of the methods appears to be especially accurate. However, one of the simplest methods, the means method, performs relatively well. Factors that lead to inaccuracies in estimation are not readily evident based on multiple regression analysis. We urge caution in the utilization of these techniques, and advocate further analysis of simulated data. Am J Phys Anthropol 110: 95-104, 1999.