Kalman filtering of consistent forward rate curves: a tool to estimate and model dynamically the term structure

Abstract

Listen

Translate article

This work explores an original methodology to specify Gaussian dynamic term structure models and estimate them efficiently from time series data. The emphasis is on the cross-sectional dimension of the problem. The form of the term premium is chosen so as to take into account the recent contributions that provide evidence in favor of time-varying market prices of risk. A model based on a widely used family of forward curves is then estimated from time series of eight UK interest rates. An extensive diagnostic check is carried out to assess the fit of the model.