Clinically significant but impractical? A response to Hageman and Arrindell

Abstract

Hageman, and Arrindell [Hageman, W.J., & Arrindell, W.A. (in press). Establishing clinically significant change: increment of precision and the distinction between individual and group level of analysis. Behavior Research and Therapy.] suggest adaptations to the traditional clinical significance model originally developed by Jacobson, Follette, and Revenstorf [Jacobson, N.S., Follette, W.C., & Revenstorf, D. (1984). Toward a standard definition of clinically significant change. Behavior Therapy, 17, 308-311.]. They observe that one must distinguish between analysis at the individual and group level and based upon an alternative decision-making strategy have formulated different procedures for assessing clinically significant change that incorporate the unreliability inherent in testing measures. A comparison of the traditional method with Hageman and Arrindell's suggested approach is conducted utilizing data originally presented by Jacobson and Truax [Jacobson, N.S., & Truax, P.,

Clinical significance: a statistical approach to defining meaningful change in psychotherapy research. Journal of Consulting and Clinical Psychology, 59, 12-19.] and implications of this comparison for the method developed by Hageman and Arrindell's method are discussed. Although this revised method has much to recommend it, it seems to yield results at the individual level that are quite similar to those derived from the traditional method. Given the complexity of the revised method, the traditional model developed by Jacobson, Follette, and Revenstorf (1984) still seems to be preferable.