Use of lags in supplementary cards

A forum for questions and answers regarding the CATS cointegration procedure

Use of lags in supplementary cards

Unread postby randerson » Wed Sep 16, 2015 3:49 pm

Is there a limitation/bug in the use of supplementary cards in the @cats dialog? If I specify "dum" as an option, lags are accepted in the # supplementary card. If I specify "exo" as an option and use the same supplementary card -- Cats crashes with a Rats error re seeking to use a series numbered out of bounds. The obvious workaround is to create the lagged series with a Set instruction, entering the lagged series on the supplementary card -- then all is well. I did not see in the manual any caution regarding the use of lags in supplementary cards. Thank you.
randerson
 
Posts: 14
Joined: Wed Dec 01, 2010 12:24 pm

Re: Use of lags in supplementary cards

Unread postby TomDoan » Thu Sep 17, 2015 11:35 am

EXO variables are completely different from DUM variables. EXO variables are treated just like the endogenous variables (inclusion in lagged differences and the cointegrating relationship), except that there is no equation for them. DUM variables aren't included in the cointegrating space and don't have lags added automatically.
TomDoan
 
Posts: 7156
Joined: Wed Nov 01, 2006 5:36 pm

Re: Use of lags in supplementary cards

Unread postby randerson » Thu Sep 17, 2015 3:20 pm

Thanks, Tom. Yes, all of that I understood. What surprised me is that the "standard" Rats lag notation -- { x } is accepted when "dum" is used but traps a fatal error when "exo" is used. I had anticipated that the standard notation would work in both cases.
randerson
 
Posts: 14
Joined: Wed Dec 01, 2010 12:24 pm


Return to CATS Questions

Who is online

Users browsing this forum: No registered users and 1 guest