Σύγκριση μεθόδων

	Psychometric Meta-Analysis	Multitrait-Multimethod Matrix
Πεδίο	Οργανωσιακή Συμπεριφορά	Οργανωσιακή Συμπεριφορά
Οικογένεια	Process / pipeline	Process / pipeline
Έτος προέλευσης	1977	1959
Δημιουργός	Frank L. Schmidt & John E. Hunter	Donald T. Campbell & Donald W. Fiske; Keith F. Widaman
Τύπος	Artifact-corrected meta-analytic estimation pipeline	Construct-validation matrix and covariance-structure modeling pipeline
Θεμελιώδης πηγή	Hunter, J. E., & Schmidt, F. L. (2004). Methods of Meta-Analysis: Correcting Error and Bias in Research Findings (2nd ed.). Sage Publications. ISBN: 9781412904797	Campbell, D. T., & Fiske, D. W. (1959). Convergent and discriminant validation by the multitrait-multimethod matrix. Psychological Bulletin, 56(2), 81-105.
Εναλλακτικές ονομασίες	Hunter-Schmidt Meta-Analysis, Validity Generalization, Artifact-Corrected Meta-Analysis, VG	MTMM, Multitrait-Multimethod Analysis, Campbell-Fiske Matrix, CFA-MTMM
Συναφείς	3	3
Σύνοψη	Psychometric meta-analysis is the Hunter-Schmidt approach to cumulating research findings while correcting for the statistical artifacts that distort individual studies. Frank Schmidt and John Hunter developed it to solve the problem of validity generalization: across many studies the observed validity of a selection test varied widely, leading people to conclude that validity was situationally specific, when in fact most of the variation was an illusion produced by small samples, unreliable measures, and restricted ranges. Their 1977 Journal of Applied Psychology paper showed that once these artifacts are removed, the apparent variability shrinks and a stable true validity emerges that generalizes across settings. The full method, codified in their book Methods of Meta-Analysis, pools effect sizes, subtracts the variance due to sampling error, and corrects the mean and remaining variance for measurement unreliability and range restriction. It estimates not only the average true effect but how much it really varies and whether it generalizes.	The multitrait-multimethod matrix is the classic framework for establishing construct validity by measuring several traits with several methods and examining the resulting pattern of correlations. Donald Campbell and Donald Fiske introduced it in 1959, arguing that validating a construct requires showing both convergent validity — different methods of measuring the same trait agree — and discriminant validity — measures of different traits diverge even when they share a method. The matrix lays out every correlation among trait-method combinations so that these patterns can be read off systematically, while also exposing method variance, the tendency of measures sharing a method to correlate for the wrong reasons. Campbell and Fiske's original criteria were inspectional rules of thumb; Keith Widaman's 1985 work recast the matrix as a family of nested confirmatory factor models, providing formal significance tests for convergent validity, discriminant validity, and method variance. The MTMM matrix remains a foundational tool for asking whether a measure captures the construct it claims to.