Minor Bug in ADF Procedure

Questions and discussions on Time Series Analysis

Minor Bug in ADF Procedure

Postby TedKury » Tue Nov 14, 2006 9:51 am

Not sure if this is the right forum, but I'll post it here anyway.

On line 140 of the ADF procedure, the SMPL statement within the SELECTUNI subprocedure

SMPL maxlag nobs

will cause problems if series does not begin with entry 1. The line should read

SMPL startl+maxlag-1 startl+nobs-1

This should fix the problem.
TedKury
 
Posts: 7
Joined: Tue Nov 14, 2006 9:38 am
Location: Jacksonville

Postby TomM » Tue Nov 14, 2006 11:07 am

Which "ADF" procedure? Are you referring to the procedure on the old file "ADF.SRC"?

If so, that shouldn't still be available on our website anywhere, as it was superseded years ago by a newer version called "URADF.SRC". Check out URADF.SRC from our website--it should handle entry ranges properly.

Please let me know if you found a copy of ADF.SRC on the current site somewhere, or if you were referring to a different file.

Tom Maycock
Estima
Tom Maycock
Estima

support@estima.com
TomM
 
Posts: 21
Joined: Tue Oct 24, 2006 3:34 pm
Location: Evanston, IL

Postby TedKury » Tue Nov 14, 2006 12:16 pm

Thanks for the pointer, Tom. I really should use your menus to find things. Bad habit. I found the old proc at www.estima.com/procs/adf.src through the website's Search feature.
TedKury
 
Posts: 7
Joined: Tue Nov 14, 2006 9:38 am
Location: Jacksonville


Return to Other Time Series Analysis

Who is online

Users browsing this forum: No registered users and 1 guest