Abstract Partial least square regression (PLSR) is a statistical modeling technique that extracts latent factors to explain both predictor and response variation. PLSR is particularly useful as a data exploration technique because it is highly flexible (e.g., there are few assumptions, variables can be highly collinear). While gaining importance across a diverse number of fields, its application in the social sciences has been limited. Here, we provide a brief introduction to PLSR, directed towards a novice audience with limited exposure to the technique; demonstrate its utility as an alternative to more classic approaches (multiple linear regression, principal component regression); and apply the technique to a hypothetical dataset using JMP statistical software (with references to SAS software).

Vaginal vasocongestion and lubrication serve to prepare the vaginal lumen for sexual activity. Lubrication is important for sexual functioning and difficulties with lubrication are one of the most commonly reported symptoms of sexual dysfunction. Few studies have empirically examined how vasocongestion and lubrication relate to one another and there are currently no well-established measures of lubrication. In this study, we designed and tested a simple method to assess lubrication at the vaginal introitus in 19 healthy women, using litmus test strips. We examined the relationship between lubrication and vaginal vasocongestion (measured with a photoplethysmograph) when elicited by audiovisual sexual stimuli (male-female sexual interactions). Lubrication was elicited by the sexual stimuli and was strongly correlated with reports of sexual arousal. Unexpectedly, lubrication was not correlated with vasocongestion, even though the latter was also elicited by the sexual stimuli. We discuss the implications of these findings for informing our understanding of the female sexual response and the potential clinical and scientific utility of this new measure.

No abstract

Research conducted in our laboratory and in other laboratories has revealed that (1) women's genital responses to visual and auditory stimuli are strongly affected by the presence of sexual cues, but that (2) specific sexual cues (e.g., gender of actors, the presence of sexual violence) often have little impact on the magnitude of the responses-that is, similar genital responses are observed to very different sexual stimuli. In addition, (3) women's genital responses do not strongly correspond with self-reported sexual partner and activity preferences, or (4) with self-reported sexual arousal during the presentation of sexual stimuli. Taken together, these facts represent a puzzle, especially considering that men's genital responses are highly affected by specific sexual cues and strongly correspond to stated preferences and self-reported sexual arousal. One hypothesis to explain female low cue-specificity and low concordance (relative to men) is the preparation hypothesis: Women's indiscriminate genital responses serve a protective function. That is, they do not indicate or necessarily promote sexual interest and motivation, but rather prepare the vaginal lumen for possible sexual activity and therefore prevent injuries that may occur as a result of penetration. We review evidence for and against this hypothesis. We conclude that the evidence is favorable but not entirely convincing, and more work is required to reach a firm conclusion. We offer directions for future research.

We examined the latent structure and taxonicity of hypersexuality in large university and community samples of male and female respondents. Participants completed the Hypersexual Behavior Inventory (HBI) and Sexual Compulsivity Scale (SCS), each as part of larger anonymous online surveys of sexual behavior. Exploratory factor analyses (EFA) were performed in part to prepare the data for taxometric analysis and also to identify the putative dimensions underpinning each measure. Three latent dimensions were identified from each of the Sexual Compulsivity Scale (dyscontrol, consequences, and preoccupation) and Hypersexual Behavior Inventory (coping, dyscontrol, and consequences). Taxometric analyses of the generated factors using mean above minus below a cut (MAMBAC), maximum covariance (MAXCOV), and latent mode factor analysis (L-Mode) broadly supported a dimensional latent structure for hypersexuality, particularly in female participants. Implications pertaining to the assessment of hypersexuality are discussed.