American Economic Review: Vol. 104 No. 5 (May 2014)

Expand

Quick Tools:

Print Article Summary
Export Citation
Sign up for Email Alerts Follow us on Twitter

Explore:

AER - All Issues

AER Forthcoming Articles

Weak Identification in Maximum Likelihood: A Question of Information

Article Citation

Andrews, Isaiah, and Anna Mikusheva. 2014. "Weak Identification in Maximum Likelihood: A Question of Information." American Economic Review, 104(5): 195-99.

DOI: 10.1257/aer.104.5.195

Abstract

In this paper we connect the discrepancy between two estimates of Fisher information, one based on the quadratic variation of the score and the other based on the negative Hessian of the log-likelihood, to weak identification. Classical asymptotic approximations assume that these two estimates are asymptotically equivalent, but we show that this equivalence fails in many weakly identified models, which can distort the behavior of the MLE. Using a stylized DSGE model we show that the discrepancy between information estimates is large when identification is weak.

Article Full-Text Access

Full-text Article

Additional Materials

Authors

Andrews, Isaiah (MIT)
Mikusheva, Anna (MIT)

JEL Classifications

C22: Single Equation Models; Single Variables: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes
C32: Multiple or Simultaneous Equation Models: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes
E13: General Aggregative Models: Neoclassical


American Economic Review


Quick Tools:

Sign up for Email Alerts

Follow us on Twitter

Subscription Information
(Institutional Administrator Access)

Explore:

AER - All Issues

AER - Forthcoming Articles

Virtual Field Journals


AEA Member Login:


AEAweb | AEA Journals | Contact Us