Dichotomization of continuous variables: the implications for meta-analysis
Article Abstract:
In many studies included in meta-analyses, the independent variable measure, the dependent variable measure, or both, have been artificially dichotomized, attenuating the correlation from its true value and resulting in (a) a downward distortion in the mean correlation and (b) an upward distortion in the apparent real variation of correlations across studies. We present (a) exact corrections for this distortion for the case of in which only one of the variables have been artificially dichotomized and (b) methods for making approximate corrections when both variables have been artificially dichotomized. These approximate corrections are shown to be quite accurate for most research data. Methods for weighting the resulting corrected correlations in meta-analysis are presented. These corrections make it possible for meta-analysis to yield approximately unbiased estimates of mean population correlations and their standard deviations despite the initial distortion in the correlations from individual studies. (Reprinted by permission of the publisher.)
Publication Name: Journal of Applied Psychology
Subject: Social sciences
ISSN: 0021-9010
Year: 1990
User Contributions:
Comment about this article or add new information about this topic:
Individual differences in output variability as a function of job complexity
Article Abstract:
The hypothesis was tested that the standard deviation of employee output as a percentage of mean output - SD(subset p) - increases as a function of the complexity level of the job. The data examined were adjusted for the inflationary effects of measurement error and the deflationary effects of range restriction on observed SD(subset p) figures, refinements absent from previous studies. Results indicate that SD(subset p) increases as the information-processing demands (complexity) of the job increase; the observed progression was approximately 19%, 32%, and 48%, from low to medium to high complexity non-sales jobs, respectively. SD(subset p) values for sales jobs are considerably larger. These findings have important implications for the output increases that can produced through improved selection. They may also contribute to the development of a theory of work performance. In addition, there may be implications in labor economics. (Reprinted by permission of the publisher.)
Publication Name: Journal of Applied Psychology
Subject: Social sciences
ISSN: 0021-9010
Year: 1990
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: Spiritual intimacy in later life: implications for clinical practice. A tribute to adaptability: mental illness and dementia in intimate late-life relationships
- Abstracts: A reexamination of the relation between halo error and accuracy. Cognitive categorization and quality of performance ratings
- Abstracts: Sampling variance in attenuated correlation coefficients: a Monte Carlo study. Averaging correlation coefficients: Should Fisher's z transformation be used?