Page 1 of 1

BP Chisquare test of SUR system estimation

Posted: Tue Mar 03, 2015 7:29 am
by thomas84
Hello,

I have created a system estimation using SUR method. I would like to test the null hypothesis of independence using a Breusch Pagan test and chisquare distribution table values. How can I do this in Eviews? I have tried to use the command window with @chisq(x,v). I assume that x represent the name of the system and v degrees of freedom. However, I get the error message "System sent to a function which operates on a matrix". How can I resolve this issue?

Thank you.

Best
Thomas

Re: BP Chisquare test of SUR system estimation

Posted: Wed Mar 11, 2015 3:21 am
by thomas84
Hi again,

I guess my question is too general. I have actually now calculated the Breusch Pagan Test indivudally using the correlation matrix from the OLS regression given in Eviews and compared with the Chi-square critical table values. I assume there is only an uppertail test for this? The command "@chisq(x,v)" probably relates to receiving the corresponding p-value. However, if anyone knows how to do the Breusch-Pagan test for an SUR system equation please let me know.