GEOLOGY 002 Lecture Notes - Lecture 13: Instrumental Variable, Well-Founded Relation, Impossible Princess
Document Summary
Angst and pischke: the credibility revolution in empirical economics: how better research design is taking the con out of econometrics. Leamer criticizes the fact that nobody takes the other"s data analysis seriously proposes sensitivity analysis to show the variation in results with changes in specification and functional form credibility revolution. Improvement primarily through a focus on the quality of empirical research design: experiments can be a powerful method (mexico: progresa project, etc. 1. 2 the deterrent effect of capital punishment: much of applied econometrics in 1970s and early 1980s lack credibility, use of short time series with strong trends common to both dependent and independent variables; lack of credible research design. 2. 2 fewer distractions: today"s applied economists have the benefit of a less dogmatic understanding of regression analysis. In the interests of replicability, and to reduce the scope for errors, modern applied researchers often prefer simpler estimators though they might be giving up asymptotic efficiency.