Pronósticos de la estructura temporal de las tasas de interés en México con base en un modelo afín

Abstract

This paper shows that an affine model allows to equalize or improve the forecasts of the term structure of interest rates in Mexico. The forecasting model is a linear relationship between interest rates and three observable factors, using maturities 1-60 months. Affine model predictions are compared with those of forward rates, AR(1), VAR(1), and random walks. Affine model has a performance comparable to other models for horizons of 12- and 18-months, except for the random walk, which presents smaller forecast for maturities of 24- and 36- months. However, improving its forecasting performance for the 24- month horizon, and especially for 60-month maturities.