Estimation and testing the multifactor Cox-Ingersoll-Ross model of the term structure

The objective of this research is to estimate and test multifactor versions of the Cox-Ingersoll-Ross (CIR) model of the nominal term structure of interest rates. We suggest to use a state-space approach that integrates time series and cross-sectional aspects of the CIR model. It is consistent with the underlying economic model, and can utilize information from all available points of the term structure. We recover estimates of the underlying factors which are consistent with the assumptions about the stochastic processes, and compare them to factors obtained from standard factor analysis.
maximum-likelihood estimation, state-space models