Metaregresja jako metoda porządkowania empirycznych doniesień naukowych

• Autorzy: Krystyna Strzała

Warianty tytułu

Meta-regression Analysis as a Method for Synthesising Empirical Economic Research

• Języki publikacji: PL

Abstrakty

Metaanaliza (MA) jest to zestaw metod statystycznych stosowanych do porządkowania i oceny wyników empirycznych. Metaregresja (MRA) jest formą metaanalizy szczególnie przydatną w ocenie empirycznych doniesień w zakresie weryfikacji hipotez ekonomicznych. W artykule przedstawiono proces wnioskowania z wykorzystaniem metaregresji, omówiono teoremat Ricarda oraz przedstawiono zastosowanie MRA do obliczenia odchyleń realnego kursu równowagi.

EN

This paper presents and discusses the strengths and weaknesses of meta-regression analysis as a method for reviewing, analysing, summarising and evaluating empirical economic research. Meta-analysis (MA) can be viewed as a statistical tool used to combine results from independent studies to reach conclusions and is applied widely in medicine and psychology. When conducted, it becomes a part of a larger systematic review, the process involved in synthesising quantitative results of independent studies on a given research problem. Over the last twenty-five years there have been hundreds of meta-analyses carried out in medicine and the social sciences, often revealing unexpected results or resolving controversies. Meta-regression analysis (MRA) is a form of meta-analysis especially useful for reviewing and evaluating empirical research devoted to evaluating an economic hypothesis in which the process of evaluation very often concentrates on the value of the parameter of interest or other summary statistic. In meta-regression analysis, the dependent variable is a summary statistic, i.e. a regression parameter drawn from the primary study, while the independent variables may include data characteristics, specification of the model or of the employed estimation method. The results of meta-regression analysis can identify to what extent the specific characteristics of the primary study, e.g. characteristics of the data (time- or a cross section span of the data), characteristics of the underlying model (inclusion or exclusion of the specific variables), choice of estimation method and statistical inference can influence the results of the primary, individual study. The theoretical part of the paper is illustrated with examples of MRA applied to evaluate the empirical evidence on the Ricardian equivalence theorem and equilibrium exchange rates in Central and Eastern Europe. (original abstract)

Słowa kluczowe

PL

Metody statystyczne; Wnioskowanie statystyczne; Modele regresji; Metaanaliza; Równoważność ricardiańska

EN

Statistical methods; Inferential statistics; Regression models; Meta-analysis; Ricardian equivalence

• Czasopismo: Studia i Prace Uniwersytetu Ekonomicznego w Krakowie
• Rocznik: 2010
• Numer: nr 10
• Strony: 13--23

Twórcy

autor

Krystyna Strzała

• Uniwersytet Gdański

Bibliografia

• Ankem K. [2005], Approaches to Meta-analysis: A Guide for LIS Researchers, "Library & Information Science Research", vol. 27.
• Barro R.J. [1989], The Ricardian Approach to Budget Deficits, "Journal of Economic Perspectives", vol. 3.
• Doucouliagos H., Paldam M. [2008], Aid Effectiveness on Growth: A Meta Study, "European Journal of Political Economy", vol. 24.
• Egert В., Halpern L. [2006], Equilibrium Exchange Eates in Central and Eastern Europe: A Meta-regression Analysis, "Journal of Banking & Finance", vol. 30.
• Krawczyk M. [2007], O neutralności długu publicznego. Wokół ricardiańskiego teorematu ekwiwaletności - R. Barro, J. Tobin i inni, Oficyna Wydawnicza Szkoły Głównej Handlowej, Warszawa.
• Leiderman L., Blejer M. I. [1988], Modeling and Testing Ricardian Equivalence: A Survey, "International Monetary Fund Staff Papers", vol. 35.
• O'Driscoll G.P. [1977], The Ricardian Nonequivalence Theorem, "Journal of Political Economy", vol. 85.
• Stanley Т.О. [2001], Wheat from Chaff: Meta-analysis as Quantitative Literature Review, "Journal of Economic Perspectives", vol. 15.
• Stanley Т.О., Doucouliagos H., Jarrell S.B. [2008], Meta-regression Analysis as the Socio-economics of Economics Research, "The Journal of Socio-Economics", vol. 37.