Estimation of Affine Term Structure Models with Spanned or Unspanned Stochastic Volatility
We develop new procedures for maximum likelihood estimation of affine term structure models with spanned or unspanned stochastic volatility. Our approach uses linear regression to reduce the dimension of the numerical optimization problem yet it produces the same estimator as maximizing the likelihood. It improves the numerical behavior of estimation by eliminating parameters from the objective function that cause problems for conventional methods. We find that spanned models capture the cross-section of yields well but not volatility while unspanned models fit volatility at the expense of fitting the cross-section.
We thank Yacine Ait-Sahalia, Boragan Aruoba, Michael Bauer, Alan Bester, John Cochrane, Frank Diebold, Rob Engle, Jim Hamilton, Chris Hansen, Guido Kuersteiner, Ken Singleton, two anonymous referees, and seminar and conference participants at Chicago Booth, NYU Stern, NBER Summer Institute, Maryland, Bank of Canada, Kansas, UMass, and Chicago Booth Junior Finance Symposium for helpful comments. Drew Creal thanks the William Ladany Faculty Scholar Fund at the University of Chicago Booth School of Business for financial support. Cynthia Wu also gratefully acknowledges financial support from the IBM Faculty Research Fund at the University of Chicago Booth School of Business. This paper was formerly titled "Estimation of non-Gaussian affine term structure models." The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research.
Creal, Drew D. & Wu, Jing Cynthia, 2015. "Estimation of affine term structure models with spanned or unspanned stochastic volatility," Journal of Econometrics, Elsevier, vol. 185(1), pages 60-81. citation courtesy of