Power is an indicator of the ability of a statistical analysis to detect a phenomenon that does in fact exist. The issue of power is crucial for social science research because sample size, effects, and relationships studied tend to be small and the power of a study relates directly to the size of the effect of interest and the sample size.…

From a cognitive perspective, racial bias is evident when raters weigh job-relevant information differentially as a function of ratee race. The results of studies that have examined this issue have been conflicting. Meta-analytic procedures were used to provide more definitive conclusions as to whether supervisor ratings are more strongly related…

Applied the meta-analysis technique to school-based studies of psychotherapy. The results indicate that psychotherapy in the schools is moderately effective. Evidence was also found of the greater efficacy of group and behavioral theory interventions that target observed behaviors and problem-solving abilities. (Author/KS)

This paper provides a summary of cost-benefit and cost-effectiveness analyses and their potential importance for decision making. The extent to which these tools are actually used, the possible connections between meta-analysis and cost-effective analysis, and the connection between effect sizes and benefit-cost ratios are discussed. (JAZ)

Meta-research study examined ongoing research projects of personal autonomy initiative of Retirement Research Foundation. Developed guidelines emphasizing appropriate setting and context of review for research in long term care, clinical assessment of decisional capacity, and institutional arrangements to minimize conflict of interest. (Author)

This article describes conceptual and methodological limitations of existing research on the efficacy of early intervention programs. Recent studies using meta-analytic techniques to generate testable hypotheses are reviewed. Recommendations for greater precision in measurement and for improved research design are offered. (DB)

The article reviews 25 studies investigating peer status of learning disabled children. An underlying assumption of most of the studies was a unidirectional relationship between peer status and social skills. The studies are reinterpreted using a bidirectional model in which peer status is the outcome of reciprocal interactions between child,…

Meta analysis is used to examine the results of 189 studies concerning sex and intelligence. The relationship between these two variables is investigated for five large clusters of cultures. For some intelligence factors, significant cultural differences are found between Western groups and Asian/African groups. (VM)

This introduction to meta-analysis uses examples of data reported for normal-hearing students, hearing-impaired students, and a comparison of the significance of the difference between the two. The analysis shows instruction in thinking strategies (metacognition) to be an appropriate classroom technique for improving learning with normal-hearing…

Examines 2,000 Strange Situation classifications obtained in eight different countries. Differences and similarities between distributions in classifications of samples are investigated using correspondence analysis. Substantial intracultural differences are established; data also suggest a pattern of cross-cultural differences. (Author/RWB)

Conducted meta-analysis with 23 studies to assess relationship between supervisory ratings and results-oriented measures of performance. Corrected mean correlation was higher when relative (versus absolute) rating format was used and when composite (versus overall) rating method was used. Differences did not account for all remaining variance…

There are numerous micro-level methods decisions associated with planning an impact evaluation. Quantitative synthesis methods can be used to construct an actuarial data base for establishing the likelihood of achieving desired sample sizes, statistical power, and measurement characteristics. (Author/BS)

The manner in which results and methods are reported influences the ability of the synthesis of prior studies for planning new evaluations. Confidence ratings, coding conventions, and supplemental evidence can partially overcome the difficulties. Planners must acknowledge the influence of their own judgement in using prior research. (Author)

Results of three forms of meta-analysis on 41 studies involving behavior disorders revealed powerful effects of treatment: both interventions targeting classroom behavior and those attributable to a behavioral orientation were somewhat more powerful and robust. Methodological flaws, however, are cited. Recommendations for solidifying the research…

Solutions to methodological problems in medical technologies research synthesis relating to temporal change, persons receiving treatment, research design, analytic procedures, and threats to validity are presented. These solutions should help with the planning and methodogy for research synthesis in other areas. (BS)