Paper result replication


I am trying to replicate the results of:

"Efficient Tests of Long-Run Causation in Trivariate VAR Processes
with Rolling Window Study of the Money-Income Relationship."
Journal of Applied Econometrics 22, 747-765.

The author has two codes, one for trivariate and one for bivariate.

The data is here.

With both, I m getting errors (in particular error line 1593 & 2055)

Thank you for your help


2 Answers


Hello Jamal,

I am able to run the code to completion without error. I had to change the data loading line from this:

load W[528,8] = c:\GAUSS50\temp\DIM1M2r_m_sa.txt;

to this

load W[528,6] = jbhill-income-data.txt;

because the data file name was different and the jbhill-income-data.txt file only has 6 variables. If you leave the load W[528,8], you will get some strange errors, because the data is this file is not 528x8.

If this does not resolve your error, please post the exact error message that you are receiving along with the code from the line of the error and any changes you made to the data loading statement.


Thank you so much. I should have checked the data but I did not.

Now its running like a charm. One more thing I need your help with is the black background color on the graphs.

I changed pmcolor in the code to make it white or what I thought will make it white but the graphs still print with a blackground.

You must login to post answers.

Have a Specific Question?

Get a real answer from a real person

Need Support?

Get help from our friendly experts.

Try GAUSS for 14 days for FREE

See what GAUSS can do for your data

© Aptech Systems, Inc. All rights reserved.

Privacy Policy