R(902) no room to add more variables because of width

[xell sabido]

Dears,
I am getting this error message repeatedly
no room to add more variables because of width
An attempt was made to add a variable that would have increased the memory required to store an observation beyond what is currently
possible. You have the following alternatives:
1. Store existing variables more efficiently; see help compress.
2. Drop some variables or observations; see help drop. (Think of Stata's data area as the area of a rectangle; Stata can trade off width and length.)
3. Increase the amount of memory allocated to the data area using the set memory command; see help memory.
r(902);
end of do-file

My windows is 64 bit and has a RAM of 4.00 GB. I have STATA SE 11.2.
The database contains 329,154 observations, 7 variables, size: 10,862,082 (79.3% of memory free).
I have compressed and dropped variables but the message persist
I have also tried to increase memory: set memory 2000 m, etc but message persist
And when I call *memory , I still have free memory (78.65%).
What else could I try?
Meritxell

[Maarten Buis]

You could tell us the command you tried to run...

[xell sabido]

Dear Maarten, I am trying to do a segmented regression analysis with this command:

glm aids intervention time, family (poisson)link (log) offset (logpop) eform

[Maarten Buis]

That does not look like something that should give you trouble. Is that a simplified version of your command or is that the exact command you used?

[xell sabido]

Dear Maarten, it is the exact command I used

[William Lisowski]

I'm not overly familiar with segmented regression analysis, but I do not see how the command you show us, by itself, would accomplish segmented regression analysis. Is it part of a larger set of commands, perhaps a loop, so that this command would not necessarily be the one that created a large number of variables?

Beyond that, the use of Stata 11.2 is going to limit the number of members who feel confident in commenting on your problem.

[Maarten Buis]

I really don't see a reason why you should get that error message. Your model is equivalent to: poisson aids intervention time, offset(logpop) irr . Does that work?

[xell sabido]

It works! Thanks so much for your support.

Meritxell

[Steve Samuels]

As William pointed out , you are not doing a segmented regression-your command shows linear time. To do a segmented regression, use mkspline.