Simulated Likelihood Estimation of Affine Term Structure Models from Panel Data

36 Pages Posted: 23 Feb 2006

See all articles by Michael W. Brandt

Michael W. Brandt

Duke University - Fuqua School of Business; National Bureau of Economic Research (NBER)

Ping He

Tsinghua University, SEM

Date Written: February 18, 2006

Abstract

We show how to estimate affine term structure models from a panel of noisy bond yields using simulated maximum likelihood based on importance sampling. We approximate the likelihood function of the state-space representation of the model by correcting the likelihood function of a Gaussian first-order approximation for the non-normalities introduced by the affine factor dynamics. Depending on the accuracy of the correction, which is computed through simulations, the quality of the estimator ranges from quasi-maximum likelihood (no correction) to exact maximum likelihood as the simulation size grows.

Keywords: Term Structure, State-Space Representation, Importance Sampling, Simulated Likelihood

JEL Classification: C13, C15, G13

Suggested Citation

Brandt, Michael W. and He, Ping, Simulated Likelihood Estimation of Affine Term Structure Models from Panel Data (February 18, 2006). Available at SSRN: https://ssrn.com/abstract=885682 or http://dx.doi.org/10.2139/ssrn.885682

Michael W. Brandt (Contact Author)

Duke University - Fuqua School of Business ( email )

1 Towerview Drive
Durham, NC 27708-0120
United States

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Ping He

Tsinghua University, SEM ( email )

Beijing, 100084
China
8610-62795754 (Phone)
8610-62784554 (Fax)

HOME PAGE: http://www.sem.tsinghua.edu.cn/en/heping

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
301
Abstract Views
1,705
Rank
183,357
PlumX Metrics