Érudit | Dépôt de documents >
CIRPÉE - Centre interuniversitaire sur le risque, les politiques économiques et l'emploi >
Cahiers de recherche du CIRPÉE >

Please use this identifier to cite or link to this item:

Title: Nonlinear Kalman Filtering in Affine Term Structure Models
Authors: Christoffersen, Peter
Dorion, Christian
Jacobs, Kris
Karoui, Lotfi
Keywords: Kalman filtering
Term structure models
Issue Date: 2014-01
Series/Report no.: Cahiers du CIRPÉE;2014-04
Abstract: The extended Kalman filter, which linearizes the relationship between security prices and state variables, is widely used in fixed income applications. We investigate if the unscented Kalman filter should be used to capture nonlinearities, and compare the performance of the Kalman filter to that of the particle filter. We analyze the cross section of swap rates, which are mildly nonlinear in the states, and cap prices, which are highly nonlinear. When caps are used to filter the states, the unscented Kalman filter significantly outperforms its extended counterpart. The unscented Kalman filter also performs well when compared to the much more computationally intensive particle filter. These findings suggest that the unscented Kalman filter may prove to be a good approach for variety of problems in fixed income pricing.
Appears in Collections:Cahiers de recherche du CIRPÉE

Files in This Item:

CIRPEE14-04.pdf, (Adobe PDF ; 1.95 MB)

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.


About Érudit | Subscriptions | RSS | Terms of Use | Contact us |

Consortium Érudit ©  2016