DNS.forecast: Dynamic Nelson-Siegel Forecasting for Yield Curves

In ottosven/dffm: Approximate Functional Factor Model

Dynamic Nelson-Siegel Forecasting for Yield Curves

Description

DNS.forecast implements the Dynamic Nelson-Siegel (DNS) model of Diebold and Li (2006) to forecast yield curves. The function accommodates both Vector Autoregression (VAR) and Autoregressive (AR) models. This function is designed to work with preprocessed functional data objects (fdaobj).

Usage

DNS.forecast(
  fdaobj,
  p = 1,
  AR = FALSE,
  obsdata = FALSE,
  start = NULL,
  end = NULL,
  h = 1
)

Arguments

fdaobj	An object of class fdaobj.
p	Integer defining the number of lags to include in the VAR model.
AR	A logical flag indicating whether to model individual AR(p) processes (TRUE) for each factor, or a collective VAR(p) model (FALSE). Default is FALSE.
obsdata	A logical flag indicating whether to use the raw data (TRUE) or the preprocessed data (FALSE) from fdaobj. Default is FALSE.
start	Optional integer specifying the start index for a restricted sample period.
end	Optional integer specifying the end index for a restricted sample period.
h	An integer specifying the forecast horizon. If h=0, an in-sample fit is returned. For h > 0, an out-of-sample h-step forecast is generated. Default is h=1.

Value

The function returns different outputs based on the value of h. If h > 0: Returns the h-step ahead forecasted curve. If h = 0: Returns a list containing:

curve.predict	The in-sample predicted curves.
factors.predict	The in-sample predicted factors.
NSloadings	The Nelson Siegel loadings.
betas	The estimated betas (factors) in the Nelson-Siegel model.
VARmatrix	The estimated VAR matrix.

References

• Diebold, F. X., & Li, C. (2006). Forecasting the term structure of government bond yields. Journal of Econometrics, 130(2), 337-364.

Examples

# Load, preprocess data, and perform in-sample prediction
fed = load.fed()
fdaobj = fda.preprocess(data = fed)
in_sample_fit = DNS.forecast(fdaobj, h=0)

# Perform 1-step ahead prediction
one_step_ahead = DNS.forecast(fdaobj, h=1)

ottosven/dffm documentation built on Feb. 23, 2025, 1:15 p.m.