caa a22 4500 477121802 CHVBK 20180405111638.0 cr unu---uuuuu 170330e19961201xx s 000 0 eng 10.1007/BF02229141 doi (NATIONALLICENCE)springer-10.1007/BF02229141 Hsu Louis Department of Psychology, Fairleigh Dickinson University, 1000 River Road, 07666, Teaneck, New Jersey aut On the identification of clinically significant client changes: Reinterpretation of Jacobson's cut scores [Elektronische Daten] [Louis Hsu] "Cut points” or "cut scores” play a central role in Jacobson's popular method of identifying clinically significant changes in psychotherapy. When pre- and posttherapy scores of a client are on different sides of one of these cut scores, the change is considered clinically significant, provided that it is also "reliable” (i.e., not due to measurement errors). This article critically examines the meanings and implications of these cut scores. Contrary to popular beliefs, they are generallynot the test scores for which the probability of "belonging” to the Functional population is equal to the probability of "belonging” to the Dysfunctional population. When the Functional population distribution is above that of the Dysfunctional population, persons scoring above these cut scores can, in fact, have much greater probabilities of belonging to the Dysfunctional than to the Functional population. Goals of Jacobson's method can be attained only with Bayesian methods. Bayesian modifications of Jacobson's cut scores are proposed, although their use is limited by the availability of relevant base rates. Bayesian methods (a) can provide information about the probability that an individual belongs to each population, given his (her) score, and (b) are expected to yield total misdiagnosis rates that are many times lower than those of Jacobson's method. Users of Jacobson's method are cautioned against interpreting ratios of likelihoods as if they were ratios of posterior probabilities. Plenum Publishing Corporation, 1996 Bayesian methods nationallicence change scores nationallicence cut scores nationallicence clinical significance nationallicence Journal of Psychopathology and Behavioral Assessment Kluwer Academic Publishers-Plenum Publishers 18/4(1996-12-01), 371-385 0882-2689 18:4<371 1996 18 10862 https://doi.org/10.1007/BF02229141 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF02229141 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Hsu Louis Department of Psychology, Fairleigh Dickinson University, 1000 River Road, 07666, Teaneck, New Jersey aut NATIONALLICENCE 773 0- Journal of Psychopathology and Behavioral Assessment Kluwer Academic Publishers-Plenum Publishers 18/4(1996-12-01), 371-385 0882-2689 18:4<371 1996 18 10862 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer