This article reports on a research project aimed at evaluating the potential for using DSP2 software in forensic anthropological casework by performing the following tasks: intra- and interobserver error analyses of all 10 measurements in DSP2, an assessment of the accuracy and inclusivity of DSP2 on a large sample of known individuals form modern U.S. skeletons, and by comparing the results o previous tests based on the number of measurements available for analysis.
Sex estimation is a critical component of the biological profile, and forensic anthropologists may use a variety of sex estimation methods depending upon the degree of completeness and state of preservation of the skeletal remains being analyzed. The innominate is widely accepted to be the most sexually dimorphic skeletal element. The Diagnose Sexuelle Probabiliste (DSP) method, which uses 10 measurements of the innominate, was introduced in 2005 and updated as DSP2 in 2017. While DSP2 has been reported to have high classification accuracy rates in studies of South American and European populations, the method has not been widely tested in US samples, and few US practitioners incorporate this method into their casework. The goal of this study was to test the reliability and accuracy of DSP2 using a large, modern sample from the US (n = 174). Two observers, blinded from demographic information associated with each specimen, collected the DSP2 metrics. Intra- and interobserver error analyses showed acceptable levels of agreement for all measurements, except for IIMT. Classification accuracies exceeded 95 percent, with minimal sex bias, for both observers and using various measurement combinations; however, an inclusivity sex bias occurred with more males reaching the 0.95 posterior probability threshold required by DSP2 to provide a sex classification estimate. Based on its high accuracy, forensic anthropologists in the US may consider incorporating DSP2 into their casework, although we recommend excluding IIMT and using SPU with caution. Additional methods will continue to be needed when the posterior probability threshold is not reached. (Published Abstract Provided)