This article illustrates a simplified time series analysis for use by the counseling researcher practitioner in single-case baseline plus intervention studies with a Bayesian probability analysis to integrate findings from replications. The C statistic is recommended as a primary analysis tool with particular relevance in the context of actual…

This article illustrates 2 follow-up procedures that can be used to examine multivariate analysis of variance (MANOVA) group differences: the univariate analysis of a linear composite variable and multivariate contrasts. A heuristic data set is used to demonstrate the procedures, and it is shown that the follow-up methods will not always yield…

Estimated statistical power for three randomization tests used with multiple-baseline designs using Monte Carlo methods. For an effect size of 0.5, none of the tests provided an adequate level of power, and for an effect size of 1.0, power was adequate for the Koehler-Levin test and the Marascuilo-Busk test only when the series length was long and…

Five focus group sessions involving 35 persons associated with Research for Better Schools had to initiate a needs assessment. Tapes and transcripts of the sessions were analyzed. Analyses support the value of the focus groups in providing input to the design of the needs assessment survey. (TJH)

Reviews Gordon and Shontz' (1990) article on Representative Case Research (RCR) with emphasis on its contributions to science and practice integration in helping professions. Raises RCR policy issues concerning potential for dual relationships and academic institution and service agency policies that could hamper RCR's widespread adoption.…

Examines the nature of empirical research in six public administration-related journals by focusing on the purpose of published research, research designs, and statistical techniques. Suggests that a cumulative knowledge base is not being developed by public administration scholars. (Author/JOW)

Discusses a 1993 study by Frazier, d'Arcais, and Coolen intended to test Schreuder's (1990) Morphological Integration model concerning the processing of separable and inseparable verbs. Suggests that the logic of the experiment is flawed and that the data do not warrant the author's conclusions. (DR)

Discusses a 1993 study by Frazier, d'Arcais, and Coolen intended to test Schreuder's (1990) Morphological Integration model concerning the processing of separable and inseparable verbs, and attempts to refute Kempen's objections to their interpretation of the experimental results in this issue. (DR)

Discusses training costs and methods for evaluating the effectiveness of training. Topics addressed include tracking training investments; tracking individual and business performance, including measurement techniques; research designs for analyzing performance; demonstrating return on investment; reasons for low return on investment; and ways to…

Notes that longitudinal data can play an important role in child psychopathology and treatment. Introduces review of some of the research questions that longitudinal designs can answer and how longitudinal studies have been used in evaluating traditional syndromes in child clinical psychology. (Author/NB)

Responds to previous article (Thomas, 1990) by discussing principles of research validity and research design. Concludes that humanistic values must be maintained during the quest for knowledge and professional status. Sees ultimate goal of all endeavors of rehabilitation researchers, educators, and professionals to be promotion of welfare of…

Discusses issues to consider when investigating behavioral effect of foods, including idiosyncratic response to particular food, necessity of identifying individual sensitive to food being studied, necessity of including washout phase, consideration of withdrawal effects, assessment of change, dietary challenge, and time parameter necessary for…

Discusses two areas for improving consultation research: defining "boundary" conditions for consultation and analogue research and expanding measures used to evaluate consultation outcome research. Defines consultation as egalitarian relationship between consultant and consultee focusing on problem of third party client and resulting in…

To predict suicide, explicit causal models of suicide outcome are needed in which predictors are temporally ordered and then tested statistically. Because suicide is a dichotomous, nominal scale outcome, only certain statistics for prediction are appropriate. Logistic regression, which utilizes the likelihood ratio test of statistical inference,…

Comparison of six procedures to test for location equality among two or more groups when population variances are heterogeneous suggests that, when the variance homogeneity and normality assumptions are not satisfied, and the design is unbalanced, the use of any of these test statistics with the usual least squares estimators is not recommended.…