est.vecm.mdls: Estimation of Vector Error Correction Models

In GVAR: Vector Error Correction Model (VECM), VECM with exogenous I(1) variables, Global VAR (GVAR)

Description

est.vecm.mdls will calculate VECMs and provide trace and eigenvalue statistics to determine the cointegration rank of the system

Usage

est.vecm.mdls(Y.ts, etw, p, case, r, season = NULL, season.start.time = NULL)

Arguments

Y.ts	a time series data matrix containing the endogenous data
etw	estimation time window, a list of the form list(start=,end=,freq=)
p	lag order of the endogenous variables
case	intercept and trend options from "I" to "V", where case "I" is a zero intercept, zero trend model, case "II" is a restricted intercept, zero trend model, "III" is a unrestricted intercept, zero trend model, "IV" is a unrestricted intercept restricted trend model and "V" is a unrestricted intercept, unrestricted trend model
r	cointegrating rank used for estimating the model
season	frequency of optional seasonal dummies, default value is NULL (no seasonal dummies)
season.start.time	optional dummy start, default value is NULL

Details

Calculating VECMs:

Value

An object of class "vecm" containing the following items

type	is set to "VECM" by default
dat	data used for calculating the model
freq	frequency of the time series used
n	number of variables entering the model
p	lag order of the endogenous variables
r	cointegrating rank used for the model estimation
T	length of the time series, given without initial values
alpha	list of model coefficients for the different cointegration ranks, see details
beta	list of model coefficients for the different cointegration ranks, see details
Pi	list of model coefficients for the different cointegration ranks, see details
Gamma	list of model coefficients for the different cointegration ranks, see details
case	intercept and trend specification from "I" to "V", see arguments
mu.0	list of intercepts for the different cointegration ranks, see details
mu.1	list of trend coefficients for the different cointegration ranks, see details
Phi	list of model coefficients for the different cointegration ranks, see details
Omega	list of covariance matrices of the error terms for the different cointegration ranks
residuals	model residuals
S	product moment matrices
lambda	eigenvalues
se	standard errors of coefficients
tvalues	t-distributed test statistic of coefficients
pvalues	p-values for test statistic of coefficients

Note

~~further notes~~

Author(s)

Martin Summer, Klaus Rheinberger, Rainer Puhr, Michael Sigmund

References

Soeren Johansen. Likelihood-Based Inference in Cointegrated Vector Auto-Regressive Models. Advanced Texts in Econometrics. Oxford University Press, 1995.

Helmut Luetkepohl, Markus Kraetzig. Applied Time Series Econometrics. Cambridge University Press, 2004.

Helmut Luetkepohl. New Introduction to Multiple Time Series Analysis. Springer, 2005.

See Also

est.we.mdls

Examples

 data(RDp)

    dt <- 1/tsp(RDp)[3]
     k <- 4
   etw <- list(start=tsp(RDp)[1]+k*dt,end=tsp(RDp)[2],freq=tsp(RDp)[3])

 model <- est.vecm.mdls(Y.ts=RDp,etw=etw,p=k,r=1,case="III",season=4,season.start.time=1)
 summary(model)

GVAR documentation built on May 2, 2019, 6:30 p.m.