statehistory.pci: Generates the sequence of inferred states of a partial...

Description Usage Arguments Details Value Author(s) See Also Examples

Description

Generates the sequence of inferred states of a partial cointegration model

Usage

1
statehistory.pci(A, data = A$data, basis = A$basis)

Arguments

A

An object returned by fit.pci representing a partial cointegration fit.

data

The data history for which the inferred states are to be computed. This should be a (k+1) x n matrix, where k is the number of independent variables and n is the number of observations. If this is omitted, then uses the data history that was used in fitting the model A.

basis

The coefficients of the independent variables. This is a vector of length k. If this is omitted, then uses the coefficients that were computed in fitting the model A.

Details

Computes the expected internal states of the model over the course of the data history.

Value

Returns a data.frame with the following columns:

Y

The variable being modeled

X1,...,X_N

The independent variables

Z

The residual series Y - beta %*% X

M

The estimated state of the mean reverting component

R

The estimated state of the random walk component

eps_M

The innovation to the mean reverting component

eps_R

The innovation to the random walk component

Author(s)

Matthew Clegg matthewcleggphd@gmail.com

Christopher Krauss christopher.krauss@fau.de

Jonas Rende jonas.rende@fau.de

See Also

egcm Engle-Granger cointegration model

partialAR Partially autoregressive models

Examples

1
2
3
4
5
6
7
##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

YX <- rpci(n=1000, beta=c(2,3), sigma_C=c(0.1,0.1), rho=0.9, sigma_M=1, sigma_R=2)
f <- fit.pci(YX[,1], YX[,2:ncol(YX)])
statehistory.pci(f)

partialCI documentation built on May 1, 2019, 8:21 p.m.