XTrueSimple: Forecast for covariate matrix: using true generating process...

In yymmhaha/PackPaper1: Package related to my first paper

Description

Given the true generating process (uncorrelated 10 series), generate on into the future.

Usage

XTrueSimple(horizon, sigmax, p, ARmatrix, Xinput, nsize)

Arguments

horizon	a number. Forecast horizon.
sigmax	a number. Standard deviation of noise of x.
p	a number. Number of covariates x.
ARmatrix	a list of 3 matrices.
Xinput	a matrix. The original training X matrix for forecast, DAT$X.for.fcst (10 series)
nsize	a number. Size (nrow(Xinput)). Essentially the length of training period, used to get the end points (or starting points) of the future period.

Details

Compared to the original Xgen* which used vectorised VAR(1), here I use VAR(3) to iteratively produce future points.

Value

a matrix

X.trueforecast

a matrix. Forecast values for each series produced by true method, simple scenario.

Examples

##

yymmhaha/PackPaper1 documentation built on May 24, 2019, 8:55 a.m.