Meta-analytische Strukturgleichungsmodelle
Potenziale und Grenzen illustriert an einem Beispiel aus der Organisationspsychologie
Abstract
Zusammenfassung. Meta-analytische Ansätze gehören in der Psychologie inzwischen zum einschlägigen Methodeninventar zur Synthese empirischer Befunde und zur Ableitung evidenz-basierter Maßnahmen. Bisher dominieren univariate Ansätze, welche auf die Integration und Analyse einzelner Effektstärken abzielen und damit zur Prüfung multivariater (Kausal–)Zusammenhänge von begrenztem Wert sind. Meta-analytische Strukturgleichungsmodelle (MASEM) stellen eine hilfreiche Erweiterung dar, da sie eine meta-analytische Analyse komplexer multivariater Strukturen ermöglichen. Darüber hinaus lassen sich mittels MASEM multivariate Effektstärkenabhängigkeiten sowie Mehrebenenstrukturen abbilden. Ziel des Beitrags ist, die konzeptionellen Grundlagen von MASEM zu skizzieren und anhand eines empirischen Beispiels aus der Organisationspsychologie zu illustrieren. Den Abschluss bildet eine kritische Diskussion der Limitationen des Ansatzes. Eine englische Übersetzung als Rohfassung dieses Artikels finden Sie als Elektronisches Supplement 1.
Abstract. Meta-analyses are a important part of the methodological inventory for the synthesis of empirical findings and the derivation of evidence-based measures. So far, univariate approaches have dominated, which aim at the integration and analysis of individual effect sizes and are, thus, of limited value for testing multivariate (causal) relationships. Meta-analytical structural equation models (MASEM) represent a helpful extension, as they allow a meta-analytical analysis of complex multivariate structures. In addition, MASEM can be used to map dependencies between multivariate effect sizse and multi-level structures. The aim of this paper is to outline the conceptual foundations of MASEM and to illustrate them using an empirical example from organizational psychology. Finally, a critical discussion of the limitations of the approach will be provided.
Literatur
2010). On making causal claims: A review and recommendations. The Leadership Quarterly, 21, 1086 – 1120. https://doi.org/10.1016/j.leaqua.2010.10.010
(1993). Antecedents and consequences of salesperson job satisfaction: Meta-analysis and assessment of causal effects. Journal of Marketing Research, 30, 63 – 77.
(2015). Metasem: An R package for meta-analysis using structural equation modeling. Frontiers in Psychology, 5, 1 – 7. https://doi.org/10.3389/fpsyg.2014.01521
(2014). Modeling dependent effect sizes with three-level meta-analyses: A structural equation modeling approach. Psychological Methods, 19, 211 – 229. https://doi.org/10.1037/a0032968
(2005a). Classifying correlation matrices into relatively homogeneous subgroups: A cluster analytic approach. Educational and Psychological Measurement, 65,, 954 – 979. https://doi.org/10.1177/0013164404273946
(2005b). Meta-analytic structural equation modeling: A two-stage approach. Psychological Methods, 10 (1), 40 – 64.
(2006). How important are job attitudes? Meta-analytic comparisons of integrative behavioral outcomes and time sequences. Academy of Management Journal, 49, 305 – 325.
(1985). Statistical methods for meta-analysis. Orlando, FL: Academic Press.
(1992). A meta-analytical structural equations analysis of a model of employee turnover. Journal of Applied Psychology, 77, 890 – 909. https://doi.org/10.1037/0021-9010.77.6.890
(2007). The effects of team diversity on team outcomes: A meta-analytic review of team diversity. Journal of Management, 33, 987 – 1015. https://doi.org/10.1177/0149206307308587
(2018). Testing moderator hypotheses in meta-analytic structural equation modeling using subgroup analysis. Behavior Research Methods, 50 (4), 1359 – 1373. https://doi.org/10.3758/s13428-018-1046-3
(2016). Principles and practice of structural equation modeling (Fourth ed. Vol. 156). New York, NY: The Guilford Press.
(2001). Practical meta-analysis. Thousand Oaks, CA: Sage.
(2019). Instrumental variables two-stage least squares (2SLS) vs. maximum likelihood structural equation modeling of causal effects in linear regression models. Structural Equation Modeling: A Multidisciplinary Journal, 26, 876 – 892.
(2009). Linear causal modeling with structural equations. Boca Raton, FL: Chapman & Hall/CRC.
(2012). The competition-performance relation: A meta-analytic review and test of the opposing processes model of competition and performance. Psychological Bulletin, 138, 1035 – 1070. https://doi.org/10.1037/a0028324
(1989). Latent variable modeling in heterogeneous populations. Psychometrika, 54, 557 – 585.
(2016). Causal inference in statistics: A primer. Chichester, UK: Wiley.
(2019). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. Retrieved from: www.R-project.org
(1996). Meta-analysis and the exploration of causal mediating processes: A primer of examples, methods, and issues. Psychological Methods, 1 (1), 47 – 65.
(2016). Analyzing matrices of meta-analytic correlations: Current practices and recommendations. Research Synthesis Methods, 7, 187 – 208. https://doi.org/10.1002/jrsm.1206
(2015). Methods of meta-analysis: Correcting error and bias in research findings (3rd ed.). Thousand Oaks, CA: Sage.
(1977). Meta-analysis of psychotherapy outcome studies. American Psychologist, 32, 752 – 760.
(2003). Causation, prediction, and search. London, UK: MIT Press.
(2014). Lineare Strukturgleichungsmodelle: Eine Einführung mit R (Sozialwissenschaftliche Forschungsmethoden). München: Hampp.
(2012). Testing the circular structure of human values: A meta-analytical structural equation modeling approach. Survey Research Methods, 6 (1), 61 – 75.
(2016). How effective are behavior change interventions based on the theory of planned behavior? A three-level meta-analysis. Zeitschrift für Psychologie, 224, 216 – 233. https://doi.org/10.1027/2151-2604/a000255
(1982). Social identity and intergroup relations. Cambridge, UK: Cambridge University Press.
(2010). Conducting meta-analyses in R with the metafor package. Journal of Statistical Software, 36 (3), 1 – 48.
(1995). Theory testing: Combining psychometric meta-analysis and structural equations modeling. Personnel Psychology, 48, 865 – 885.
(2016). Fitting meta-analytic structural equation models with complex datasets. Research Synthesis Methods, 7 (2), 121 – 139. https://doi.org/10.1002/jrsm.1199
(2010).
(Effect heterogeneity and bias in main-effects-only regression models . In D. RinG. HectorY. H. Joseph (Eds.), Heuristics, Probability and Causality: A Tribute to Judea Pearl: London, UK: Kings College Publications.