There are presently three widely used methods of scoring penile circumference data. The present experiment attempted to determine the ability of each method to explain the variance within a data set. A total of 19 subjects were presented with 20 photographic slides assigned to five categories: neutral, female adult, female adolescent, male adult, and male adolescent. Erectile responses to each slide were recorded and the data analyzed in terms of the raw scores, percentage of full erection, and a z-score transformation. Results indicated that the z scores captured the highest proportion of the variance (52.7%), followed by the percentage scores (32.5%), and the raw scores (30.1%). Findings are discussed in terms of their research and clinical implications.