Calibration and modern (Bayesian) estimation methods for a neoclassical stochastic growth model are applied to make the case that the identification of key parameters, rather than quantitative methodologies per se, is responsible for empirical findings. For concreteness, the model is used to measure the contributions of technology shocks to the business cycle fluctuations of hours worked and output. Along the way, new insights are provided in the parameter identification associated with likelihood-based estimation, the sensitivity of likelihood-based estimation to the choice of structural shocks is assessed, and Bayesian model averaging is used to aggregate findings obtained from different DSGE model specifications.
Bibliographical noteFunding Information:
We thank seminar participants at the 2007 NASM, the 2007 San Sebastián Summer School, Federal Reserve Bank of Philadelphia, the 2007 CREI Conference on “How Much Structure in Macro Models,” Centro de Estudios Monetarios y Financieros, Cornell, New York University, University of Southern California, and the Wharton Macro Lunch, and Richard Rogerson for helpful comments. Data and software to replicate the empirical analysis are available on the web at http://www.ssc.upenn.edu/∼schorf . The views expressed herein are those of the authors and not necessarily those of the Federal Reserve Bank of Minneapolis or the Federal Reserve System. Ríos-Rull thanks the National Science Foundation (Grant SES-0351451 ). Schorfheide thanks the National Science Foundation (Grant SES 0617803 ). The views expressed herein are those of the authors and not necessarily those of the Federal Reserve Bank of Minneapolis or the Federal Reserve System.