jeudi 1 mars 2018

Johansen Test in R

There is a test result Johansen on cointegration.

> library("urca")
> summary(ca.jo(data.frame(price.fut.ms, price.spot.ms), type="trace", K=2, ecdet="none", 
spec="longrun"))

###################### 
# Johansen-Procedure # 
###################### 

Test type: trace statistic , with linear trend 

Eigenvalues (lambda):
[1] 0.19914009 0.01814878

Values of teststatistic and critical values of test:

          test 10pct  5pct  1pct
r <= 1 |  4.36  6.50  8.18 11.65
r = 0  | 57.21 15.66 17.95 23.52

Eigenvectors, normalised to first column:
(These are the cointegration relations)

                 price.fut.ms.l2 price.spot.ms.l2
price.fut.ms.l2         1.000000         1.000000
price.spot.ms.l2       -1.008907         0.443137

Weights W:
(This is the loading matrix)

                price.fut.ms.l2 price.spot.ms.l2
price.fut.ms.d       -0.2588310      -0.02235570
price.spot.ms.d       0.2902789      -0.02219381

How can I pull -1.008907 from the test results. In the description of functions ca.jo, nothing concrete is given on this matter

Aucun commentaire:

Enregistrer un commentaire