Article ID Journal Published Year Pages File Type
480463 European Journal of Operational Research 2012 10 Pages PDF
Abstract

Linearized versions of the Nelson–Siegel (1987) and Svensson (1994) models for the cross-sectional estimation of spot yield curves from samples of coupon bonds are developed and analyzed. It is shown how these models can be made linear in the level, slope and curvature parameters and how prior information about these parameters can be incorporated in the estimation procedure. The performance of the linearized models are assessed in a Monte Carlo setting and with a sample of US government bonds. The results reveal that the linearized models compare favorably to the original models in terms of parameter estimates stability, computing effort and prevalence of local optima.

► Linearized Nelson–Siegel–Svensson models for yield curve estimation are developed. ► The level, slope and curvature parameters of these models are linearized. ► Prior information about these parameters is incorporated in the estimation procedure. ► The results show that the proposed models produce more stable parameter estimates.

Related Topics
Physical Sciences and Engineering Computer Science Computer Science (General)
Authors
, ,