The female sexual function index (FSFI): cross-validation and development of clinical cutoff scores

Abstract

The Female Sexual Function Index (FSFI) is a brief multidimensional scale for assessing sexual function in women. The scale has received initial psychometric evaluation, including studies of reliability, convergent validity, and discriminant validity (Meston, 2003; Rosen et al., 2000). The present study was designed to crossvalidate the FSFI in several samples of women with mixed sexual dysfunctions (N = 568) and to develop diagnostic cut-off scores for potential classification of women's sexual dysfunction. Some of these samples were drawn from our previous validation studies (N = 414), and some were added for purposes of the present study (N = 154). The combined data set consisted of multiple samples of women with sexual dysfunction diagnoses (N = 307), including female sexual arousal disorder (FSAD), hypoactive sexual desire disorder (HSDD), female sexual orgasm disorder (FSOD), dyspareunia/vaginismus (pain), and multiple sexual dysfunctions, in addition to a large sample of nondysfunctional controls (n = 261). We conducted analyses on the individual and combined samples, including replicating the original factor structure using principal components analysis with varimax rotation. We assessed Cronbach's alpha (internal reliability) and interdomain correlations and tested discriminant validity by means of a MANOVA (multivariate analysis of variance; dysfunction diagnosis x FSFI domain), with Bonferroni-corrected post hoc comparisons. We developed diagnostic cut off scores by means of standard receiver operating characteristics-curves and the CART (Classification and Regression Trees) procedure. Principal components analysis replicated the original five-factor structure, including desire/arousal, lubrication, orgasm, pain, and satisfaction. We found the internal reliability for the total FSFI and six domain scores to be good to excellent, with Cronbach alpha's >0.9 for the combined sample and above 0.8 for the sexually dysfunctional and nondysfunctional samples, independently. Discriminant validity testing confirmed the ability of both total and domain scores to differentiate between functional and nondysfunctional women. On the basis of sensitivity and specificity analyses and the CART procedure, we found an FSFI total score of 26.55 to be the optimal cut score for differentiating women with and without sexual dysfunction. On the basis of this cut-off we found 70.7% of women with sexual dysfunction and 88.1% of the sexually functional women in the cross-validation sample to be correctly classified. Addition of the lubrication score in the model resulted in slightly improved specificity (from .707 to .772) at a slight cost of sensitivity (from .881 to .854) for identifying women without sexual dysfunction. We discuss the results in terms of potential strengths and weaknesses of the FSFI, as well in terms of further clinical and research implications.