VECM.test | R Documentation |
This procedure is aimed on the problem of testing for the cointegration rank of a vector autoregressive process in the case where a trend break may potentially be present in the data.
The test is based on estimating the quasi log likelihood for two situations, with break, and without it. The one with the smallest value is considered to be the result.
VECM.test(y, r, max.lag, trim = 0.15)
y |
A matrix of |
r |
The cointegration rank tested against the alternative of |
max.lag |
The maximum number of lags. |
trim |
The trimming parameter to find the lower and upper bounds of possible break dates. |
The code provided is the original GAUSS code by Harris et al. ported to R.
A list of:
the indicator of the rejection of null.
the estimated break point.
the estimated lag number.
Harris, David, Stephen J. Leybourne, and A. M. Robert Taylor. “Tests of the Co-Integration Rank in VAR Models in the Presence of a Possible Break in Trend at an Unknown Point.” Journal of Econometrics, Innovations in Multiple Time Series Analysis, 192, no. 2 (June 1, 2016): 451–67. https://doi.org/10.1016/j.jeconom.2016.02.010.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.