Smooth Dynamic Factor Analysis With Application to the Us Term Structure of Interest Rates

Abstract

SUMMARY We consider the dynamic factor model and show how smoothness restrictions can be imposed on factor loadings by using cubic spline functions. We develop statistical procedures based on Wald, Lagrange multiplier and likelihood ratio tests for this purpose. The methodology is illustrated by analyzing a newly updated monthly time series panel of US term structure of interest rates. Dynamic factor models with and without smooth loadings are compared with dynamic models based on Nelson–Siegel and cubic spline yield curves. We conclude that smoothness restrictions on factor loadings are supported by the interest rate data and can lead to more accurate forecasts. Copyright © 2013 John Wiley & Sons, Ltd.

A Bayesian Multivariate Functional Dynamic Linear Model

“…Similarly, we can interpret (1) as a dynamic factor analysis, which is a common approach in yield curve modeling (e.g., Hays et al, 2012;Jungbacker et al, 2013). Under this interpretation, the β are factor loading curves (FLCs); we will use this terminology for the remainder of the paper.…”

“…t denotes the number of observation points for outcome c at time t. The smoothness requirement is fundamental as well: as documented in Jungbacker et al (2013), smoothness constraints can improve forecasting, despite the small biases imposed by such constraints. Smooth curves also tend to be more interpretable, since gradual trends are usually easier to explain than sharp changes or discontinuities.…”

Yield curve forecast combinations based on bond portfolio performance

“…4 Finally, in order to estimate the models described in Section 3.2, an initial estimation sample of 84 monthly observations is used and it is expanded until the end of the sample is reached, leaving 81 pseudo out-of-sample monthly observations. In order to evaluate the robustness of our findings with respect to the market considered, time period analyzed, number of maturities available, and interpolation method used, we also consider a second dataset constructed by Jungbacker et al (2014). This dataset consists of fixed-maturity, end-of-month continuously compounded yields on US zero-coupon bonds from January 1970 to December 2009.…”

“…In order to evaluate the robustness of our findings with respect to the market considered, time period analyzed, number of maturities available, and interpolation method used, we also consider a second dataset constructed by Jungbacker et al (2014). This dataset consists of fixed-maturity, end-of-month continuously compounded yields on US zero-coupon bonds from January 1970 to December 2009.…”

“…The first dataset consists of constant-maturity future contracts of Brazilian interbank deposit (DI-futuro) with 14 different maturities collected on a monthly basis. In order to evaluate the robustness of our findings, we also consider a second dataset of fixed-maturity, end-of-month continuously compounded yields on US zero-coupon bonds constructed by Jungbacker, Koopman, and van der Wel (2014).…”