This function estimates a restricted VAR, where the restrictions are base upon α, i.e. the loading vectors. The test statistic is distributed as χ2 with r(p−m) degrees of freedom, with m equal to the columns of the restricting matrix A.
latin1
alrtest(z, A, r)
Arguments
z: An object of class ca.jo.
A: The (p×m) matrix containing the restrictions on α.
r: The count of cointegration relationships;
inferred from summary(ca.jo-object).
Details
The orthogonal matrix to A can be accessed as object@B. The restricted α matrix is normalised with respect to the first variable.
Returns
An object of class cajo.test.
References
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, blrtest, ablrtest, cajo.test-class, ca.jo-class and urca-class.