The primary purpose of this investigation was to examine the factor structure of the Problem Gambling Severity Index (PGSI) and the measurement equivalence/invariance between three independent datasets. Three extant datasets were examined using CFA. A two-factor model was the best fit for the construct validity of the instrument with large data sets. However, the fit was questionable for a number of models. The indicators of behaviors and consequences, within the two-factor model, indicated differential weights for men versus women raising concern about using the PGSI to make comparisons across sexes.