META‐REGRESSION ANALYSIS: A QUANTITATIVE METHOD OF LITERATURE SURVEYS
- 1 June 1989
- journal article
- Published by Wiley in Journal of Economic Surveys
- Vol. 3 (2) , 161-170
- https://doi.org/10.1111/j.1467-6419.1989.tb00064.x
Abstract
Pedagogically, literature reviews are instrumental. They summarize the large literature written on a particular topic, give coherence to the complex, often disparate, views expressed about an issue, and serve as a springboard for new ideas. However, literature surveys rarely establish anything approximating unanimous consensus. Ironically, this is just as true for the empirical economic literature. To harmonize this dissonance, we offer a quantitative methodology for reviewing the empirical economic literature. Meta‐regression analysis (MRA) is the regression analysis of regression analyses. MRA tends to objectify the review process. It studies the processes that produce empirical economic results as though they were any other social scientific phenomenon. MRA provides a framework for replication and offers a sensitivity analysis for model specification. In this brief essay, we propose a new method of reviewing economic literature, MRA, and discuss its potential.Keywords
This publication has 25 references indexed in Scilit:
- A Meta-Analysis of the Union-Nonunion Wage GapILR Review, 1990
- Forecasting from fallible data: Correcting prediction bias with stein‐rule least squaresJournal of Forecasting, 1988
- Recursive economic knowledge: Hierarchy, maximization and behavioral economicsJournal of Behavioral Economics, 1987
- On relaxing the maximization postulateJournal of Behavioral Economics, 1986
- Research Design Effects on the Reliability of Rating Scales: A Meta-AnalysisJournal of Marketing Research, 1984
- Meta-analysis of comparative therapy outcome studies: A replication and refinement.Psychological Bulletin, 1982
- Sex of researchers and sex-typed communications as determinants of sex differences in influenceability: A meta-analysis of social influence studies.Psychological Bulletin, 1981
- 9: Integrating Findings: The Meta-Analysis of ResearchReview of Research in Education, 1977
- Integrating Findings: The Meta-Analysis of ResearchReview of Research in Education, 1977
- On a Method of Determining Whether a Sample of Size n Supposed to Have Been Drawn from a Parent Population Having a Known Probability Integral has Probably Been Drawn at RandomBiometrika, 1933