Exact Maximum Likelihood Estimation of Observation-Driven Econometric Models

24 Pages Posted: 27 Aug 2000 Last revised: 23 Oct 2010

See all articles by Francis X. Diebold

Francis X. Diebold

University of Pennsylvania - Department of Economics; National Bureau of Economic Research (NBER)

Til Schuermann

Oliver Wyman

Date Written: April 1996


The possibility of exact maximum likelihood estimation of many observation-driven models remains an open question. Often only approximate maximum likelihood estimation is attempted, because the unconditional density needed for exact estimation is not known in closed form. Using simulation and nonparametric density estimation techniques that facilitate empirical likelihood evaluation, we develop an exact maximum likelihood procedure. We provide an illustrative application to the estimation of ARCH models, in which we compare the sampling properties of the exact estimator to those of several competitors. We find that, especially in situations of small samples and high persistence, efficiency gains are obtained. We conclude with a discussion of directions for future research, including application of our methods to panel data models.

Suggested Citation

Diebold, Francis X. and Schuermann, Til, Exact Maximum Likelihood Estimation of Observation-Driven Econometric Models (April 1996). NBER Working Paper No. t0194. Available at SSRN: https://ssrn.com/abstract=225100

Francis X. Diebold (Contact Author)

University of Pennsylvania - Department of Economics ( email )

Ronald O. Perelman Center for Political Science
133 South 36th Street
Philadelphia, PA 19104-6297
United States
215-898-1507 (Phone)
215-573-4217 (Fax)

HOME PAGE: http://www.ssc.upenn.edu/~fdiebold/

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Til Schuermann

Oliver Wyman ( email )

1166 6th Avenue
New York City, NY
United States

Register to save articles to
your library


Paper statistics

Abstract Views
PlumX Metrics

Under construction: SSRN citations while be offline until July when we will launch a brand new and improved citations service, check here for more details.

For more information