Item response theory analysis of Working Alliance Inventory, revised response format, and new Brief Alliance Inventory.

AbstractObjective: The Working Alliance Inventory (WAI) has made great contributions to psychotherapy research. However, studies suggest the 7-point response format and 3-factor structure of the client version may have psychometric problems. This study used Rasch item response theory (IRT) to (a) improve WAI response format, (b) compare two brief 12-item versions (WAI-sr; WAI-s), and (c) develop a new 16-item Brief Alliance Inventory (BAI). Method: Archival data from 1786 counseling center and community clients were analyzed. Results: IRT findings suggested problems with crossed category thresholds. A rescoring scheme that combines neighboring responses to create 5- and 4-point scales sharply reduced these problems. Although subscale variance was reduced by 11–26%, rescoring yielded improved reliability and generally higher correlations with therapy process (session depth and smoothness) and outcome measures (residual gain symptom improvement). The 16-item BAI was designed to maximize “bandwidth” of item ...