The Relationship Between Working Alliance and Symptom Improvement in Cognitive Therapy for Posttraumatic Stress Disorder

Abstract

Background: Working alliance has been shown to predict outcome of psychological treatments in multiple studies. Conversely, changes in outcome scores have also been found to predict working alliance ratings. Objective: To assess the temporal relationships between working alliance and outcome in 230 patients receiving trauma-focused cognitive behavioral treatment for posttraumatic stress disorder (PTSD). Methods: Ratings of working alliance were made by both the patient and therapist after sessions 1, 3, and 5 of a course of Cognitive Therapy for PTSD (CT-PTSD). Autoregressive, cross-lagged panel models were used to examine whether working alliance predicted PTSD symptom severity at the next assessment point and vice versa. Linear regressions tested the relationship between alliance and treatment outcome. Results: Both patients' and therapists' working alliance ratings after session 1 predicted PTSD symptom scores at the end of treatment, controlling for baseline scores. At each assessment point, higher therapist working alliance was associated with lower PTSD symptoms. Crossed-lagged associations were found for therapist-rated alliance, but not for patient-rated alliance: higher therapists' alliance ratings predicted lower PTSD symptom scores at the next assessment point. Similarly, lower PTSD symptoms predicted higher therapist working alliance ratings at the next assessment point. Ruminative thinking was negatively related to therapists' alliance ratings. Conclusions: Working alliance at the start of treatment predicted treatment outcome in patients receiving CT-PTSD and may be an important factor in setting the necessary conditions for effective treatment. For therapists, there was a reciprocal relationship between working alliance and PTSD symptom change in their patients during treatment, suggesting that their alliance ratings predicted symptom change, but were also influenced by patients' symptom change.

Keywords: cognitive therapy; cross-lagged associations; posttraumatic stress disorder; treatment outcome; working alliance.

Figure 1

Schematic figure of the hypothesized autoregressive, cross-lagged models. Thick paths with arrows in one direction, such as a (PDS_t → WAI_t+1; t refers to the respective treatment session and t+1 to 2 sessions later) and b (WAI_t → PDS_t+1) indicate cross-lagged effects, paths c (WAI_t → WAI_t+1) and d (PDS_t → PDS_t+1), indicate autoregressive effects; thin paths with arrows in both directions represent correlations at the same session (PDS_t ↔ WAI_t).