An Item Analysis of the Trauma Inventory for Partners of Sex Addicts

Abstract The Trauma Inventory for Partners of Sex Addicts (TIPSA) represents a pioneering attempt to measure trauma in the partners of sex addicts. In this study, we utilized a large sample of TIPSA responses to examine the impact of rescoring empirically disordered response options on error variance and scale reliability. Results suggested that rescoring by collapsing categories in response to empirical response option disordering has a mixed and marginal impact on error variance and scale reliability, and may not be beneficial from a practical standpoint in terms of reducing nuisance variation. Importantly, results also support the conclusion that measurement and diagnosis are distinct endeavors that serve two separate purposes.