Leitura do Dia - COMMENT ON ANGRIST AND PISCHKE, by CHRISTOPHER A. SIMS
CHRISTOPHER A. SIMS
I. THE BOTTOM LINE, AT THE TOP
Without apparent irony, Angrist and Pischke quote Griliches: “If the data were perfect, collected from well-designed randomized experiments, there would hardly be room for a separate field of econometrics.” The fact is, economics is not an experimental science and cannot be. “Natural” experiments and “quasi” experiments are not in fact experiments, any more than are Prescott’s “computational” experiments.
They are rhetorical devices invoked to avoid having to confront real econometric difficulties. Natural, quasi-, and computational experiments, as well as regression discontinuity design (RDD), can all, when well applied, be useful, but none are panaceas. This essay by Angrist and Pischke, in its enthusiasm for some real accomplishments in certain subfields of economics, makes overbroad claims for its favored methodologies. What the essay says about macroeconomics is mainly nonsense.
The fact that the essay is so mistaken about macroeconomics reflects a broader
problem. Recent enthusiasm for single-equation, linear, instrumental-variables approaches in applied microeconomics has led to many economists in these fields losing the ability to think formally and carefully about the central issues of non experimental inference—what Griliches saw, and I see, as the core of econometrics.
Sims, sempre afiado em suas análises. Gostei particularmente da discussão sobre o uso de mixed effect models .