Characterizing individual differences in SCR responsivity: A hybrid mixture and single-trial modeling framework.

Skin conductance responses (SCRs) are a standard index of sympathetic arousal, yet a notable proportion of individuals show low or absent SCRs and are routinely excluded from analyses. Such exclusions may reduce the representativeness of psychophysiological research and obscure genuine individual differences in autonomic responsivity. In this study, we combined conventional threshold-based classification with hierarchical and Bayesian mixture modeling to examine the continuum of SCR reactivity in 269 adults completing an auditory novelty task. Using the standard 0.02 µS criterion, 16% (42 of 261 with usable data) met non-responder criteria, meaning roughly one in six participants would typically be excluded. Among responders, a Dirichlet Process Gaussian Mixture Model revealed three latent subgroups, low-, moderate-, and high-reactive, demonstrating graded variation in SCR amplitude even within the conventionally defined responder group. Hierarchical modeling further indicated that non‑responders exhibited low‑amplitude, stimulus‑indexed SCR structure recoverable within a generative modeling framework, despite amplitudes near conventional detection thresholds. Demographic predictors were minimal, with only age showing a modest negative association with responsivity, and psychological symptoms were unrelated. Together, these findings indicate that autonomic responsivity varies continuously both within and beyond responder classification, and that rigid amplitude thresholds may obscure meaningful physiological diversity. A hybrid analytic approach that integrates traditional criteria with model-based quantification can provide a more inclusive and representative view of human autonomic variability.