urca (version 1.3-0)

ca.jo-class: Representation of class ca.jo

Description

This class contains the relevant information by applying the Johansen procedure to a matrix of time series data.

Arguments

Slots

x:

Object of class "ANY": A data matrix, or an object that can be coerced to it.

Z0:

Object of class "matrix": The matrix of the differenced series.

Z1:

Object of class "matrix": The regressor matrix, except for the lagged variables in levels.

ZK:

Object of class "matrix": The matrix of the lagged variables in levels.

type:

Object of class "character": The type of the test, either "trace" or "eigen".

model:

Object of class "character": The model description in prose, with respect to the inclusion of a linear trend.

ecdet:

Object of class "character": Specifies the deterministic term to be included in the cointegration relation. This can be either "none", "const", or "trend".

lag:

Object of class "integer": The lag order for the variables in levels.

P:

Object of class "integer": The count of variables.

season:

Object of class "ANY": The frequency of the data, if seasonal dummies should be included, otherwise NULL.

dumvar:

Object of class "ANY": A matrix containing dummy variables. The row dimension must be equal to x, otherwise NULL.

cval:

Object of class "ANY": The critical values of the test at the 1%, 5% and 10% level of significance.

teststat:

Object of class "ANY": The values of the test statistics.

lambda:

Object of class "vector": The eigenvalues.

Vorg:

Object of class "matrix": The matrix of eigenvectors, such that \(\hat V'S_{kk}\hat V = I\).

V:

Object of class "matrix": The matrix of eigenvectors, normalised with respect to the first variable.

W:

Object of class "matrix": The matrix of loading weights.

PI:

Object of class "matrix": The coeffcient matrix of the lagged variables in levels.

DELTA:

Object of class "matrix": The variance/covarinace matrix of V.

GAMMA:

Object of class "matrix": The coeffecient matrix of Z1.

R0:

Object of class "matrix": The matrix of residuals from the regressions in differences.

RK:

Object of class "matrix": The matrix of residuals from the regression in lagged levels.

bp:

Object of class "ANY": Potential break point, only set if function cajolst is called, otherwise NA.

test.name:

Object of class "character": The name of the test, i.e. `Johansen-Procedure'.

spec:

Object of class "character": The specification of the VECM.

call:

Object of class "call": The call of function ca.jo.

Extends

Class urca, directly.

Methods

Type showMethods(classes="ca.jo") at the R prompt for a complete list of methods which are available for this class.

Useful methods include

show:

test statistic.

summary:

like show, but critical values, eigenvectors and loading matrix added.

plot:

The series of the VAR and their potential cointegration relations.

Author

Bernhard Pfaff

References

Johansen, S. (1988), Statistical Analysis of Cointegration Vectors, Journal of Economic Dynamics and Control, 12, 231--254.

Johansen, S. and Juselius, K. (1990), Maximum Likelihood Estimation and Inference on Cointegration -- with Applications to the Demand for Money, Oxford Bulletin of Economics and Statistics, 52, 2, 169--210.

Johansen, S. (1991), Estimation and Hypothesis Testing of Cointegration Vectors in Gaussian Vector Autoregressive Models, Econometrica, Vol. 59, No. 6, 1551--1580.

See Also

ca.jo, plotres and urca-class.