The influence of therapist variance on the dependability of therapists' alliance scores: a brief comment on "The dependability of alliance assessments: the alliance-outcome correlation is larger than you think" (Crits-Christoph et al., 2011)

Abstract

Objective: Crits-Christoph, Connolly Gibbons, Hamilton, Ring-Kurtz, and Gallop (2011) used generalizability theory to critique the measurement of the therapeutic alliance in psychotherapy research, showing that the dependability of alliance scores may be quite low, which in turn can lead to attenuated alliance-outcome correlation estimates.

Method and results: Two extensions to Crits-Christoph et al.'s critique are presented that can greatly influence dependability of therapist scores and are particularly relevant to researchers wishing to study process-outcome correlations at the therapist level. Specifically, the authors show how the intraclass correlation and the number of therapists affect both the magnitude and precision of generalizability coefficients.

Conclusions: The authors note that attending to issues raised in this article and Crits-Christoph et al. (2011) in future process-outcome research will improve the accuracy of the conclusions about process-outcome correlations.