Implementing the Modified Nelson-Siegel-Svennson Model in Constructing the Philippine Yield Curve

page 17-20

Armin Paul D. Allado

Master of Science in Management

University of Asia and the Pacific

Ruel V. Maningas   

Doctor of Philosophy in Extension Education

University of the Philippines Los Baños

Vice Dean for Faculty Affairs and Research, School of Management, University of Asia and the Pacific

Program Director, MABA, University of Asia and the Pacific

KEYWORDS: Yield Curve, Nelson-Siegel-Svennson, Best Fit Estimation 

ABSTRACT

The main goal of this paper is to construct the Philippine yield curve using the Modified Nelson-Siegel-Svennson (NSS) model, a parametric method commonly used by economists to understand the dynamics of the yield curve. The NSS model incorporates six parameters to determine the location and magnitude of the curvature of the yield curve. Constructing the theoretical yield curve involves determining the optimal parameter values that will minimize the residual between fitted and actual yields.

The model takes as input the real-time trading data for all bonds transacted on a particular date and finds a smooth curve that best fits the observed yields using the six parameters in the NSS equation. Moreover, the model can identify which bonds are undervalued or overvalued based on the best fit curve. Furthermore, the optimal parameters of the model were analyzed to understand how they affect the best fit estimation.