Information Criteria function and Johansen Cointegration tests with dummies and exogenous variable

Hi to everybody!

I would like to ask you whether or not there exist some function in MATLAB for information criteria which allow to input the dummies and the exogenous variables as it happens in R in vars package for VARselect:

VARselect(y, lag.max = 10, type = c("const", "trend", "both", "none"),

season = NULL, exogen = NULL)

And furthermore, if there exists a similar function for the Johansen cointegration test with the same required features as for the information criteria. Please find below the correspondent function in R:

ca.jo(x, type = c("eigen", "trace"), ecdet = c("none", "const", "trend"), K = 2,

spec=c("longrun", "transitory"), season = NULL, dumvar = NULL)

I ask you this because I have to use both R and MATLAB in this period. Best regards - Niccolò Ghionzoli

Answer 1

[Karanjot]

Hi Niccolò,

I understand that you want to know about Information Criteria functions and Johansen Cointegration tests in MATLAB.

The ‘VARselect’ function in R, returns information criteria and final prediction error for sequential increasing the lag order up to a VAR(p)-proccess.

You can model the Vector autoregression process VAR(p) using a ‘varm’ object specifying the functional form and storing the parameter values of a p-order, stationary, multivariate vector autoregression model (VAR(p)) model.

Further, in order to get the information criteria, use the ‘aicbic’ function. ‘aicbic’ computes information criteria given loglikelihood values obtained by fitting competing models to data.

To perform Johansen Cointegration tests, The ‘jcitest’ function in MATLAB returns the rejection decisions h from conducting the Johansen test, which assesses each null hypothesis H(r) of cointegration rank less than or equal to r among the n-dimensional multivariate time series Y against the alternative trace test or maxeig test. The tests produce maximum likelihood estimates of the parameters in a vector error-correction (VEC) model of the cointegrated series.

To learn more about Information Criteria and Johansen Cointegration tests, please refer to the below example:

https://www.mathworks.com/help/econ/varm.html#bvn5drn-3

https://in.mathworks.com/help/econ/introduction-to-vector-autoregressive-var-models.html

https://www.mathworks.com/help/econ/aicbic.html

I hope this helps!