The Klales method of sexing pelvises includes which elements?

• A. Fewer character states, linear regression, probabilities for male vs female
• B. More character states, random forest modeling, probabilities for female vs male
• C. More character states, neural networks, discrete categories only
• D. Fewer character states, decision trees, precise sex classification

Answer: (B)

The main idea being tested is that the Klales method uses a broad set of pelvic traits and a machine-learning approach to give probabilistic sex estimates. By incorporating more character states, the method leverages a richer pattern of morphological variation, improving discrimination between male and female features rather than relying on a limited feature set. A random forest model then combines many decision trees to capture nonlinear relationships and interactions among those traits, which traditional linear methods can miss. The result is a probability for female versus male, reflecting the strength of the data rather than a forced yes/no classification. This probabilistic approach is more informative for forensic interpretation and can be better calibrated across populations. Other options imagine fewer traits or different algorithms that either reduce information or produce only discrete, non-probabilistic classifications, which is less consistent with how Klales operates.