st: dropped from div() using xtabond or xtdpdsys

[Mike McDonald <mimcdonald03@gmail.com>]

Dear statalisters: I posted this message to the group last week and
did not receive any responses. I deeply wish to respect your time and
avoid cluttering your inboxes, but I want to make sure my message was
not simply overlooked. I will repost just once and then assume that if
no one responds I am on my own! I do appreciate any help...

Hi all,

I'm new to panel data methods in STATA and have a question. Using
xtabond and xtdpdsys I get a note accompanying the output that says
"ip dropped from div() because of collinearity". The variable ip is
one of my primary explanatory variables. I am trying to understand
this note.

As best I can tell, STATA is telling me that the variable was dropped
from the difference equation. But I'm not sure what the implications
of this are.

What exactly does that mean? Does it matter? And most importantly,
does it affect the coefficient and significance test of the ip
variable in the regression results?

Thanks!

Mike McDonald
University of Maryland
mkm@umd.edu
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/