GMM Estimation of Affine Term Structure Models

TL;DR

This paper develops a GMM-based estimation approach for affine term structure models, utilizing polynomial process results and Quasi-Bayesian methods to obtain reliable parameters and apply them to real interest rate data.

Contribution

It introduces a novel GMM estimation framework for affine models that combines polynomial process moments with Quasi-Bayesian inference, enhancing estimation reliability.

Findings

Successful estimation of affine model parameters from simulated data

Application to empirical interest rate data demonstrates practical utility

Improved inference accuracy over traditional methods

Abstract

This article investigates parameter estimation of affine term structure models by means of the generalized method of moments. Exact moments of the affine latent process as well as of the yields are obtained by using results derived for p-polynomial processes. Then the generalized method of moments, combined with Quasi-Bayesian methods, is used to get reliable parameter estimates and to perform inference. After a simulation study, the estimation procedure is applied to empirical interest rate data.