Tim,
There is a FAQ on approximating the memory requirements of a dataset at: http://www.stata.com/support/faqs/data/howbig.html
The basic formula is
"A back-of-the-envelope calculation for the size of a dataset is
N*V*W + 4*N
number of megabytes = M = --------------
(1024)^2
where
N = number observations
V = number of variables
W = average width in bytes of a variable
In approximating W, remember
+-------------------------------------------------------------+
| Type of variable Width |
|-------------------------------------------------------------|
| Integers, -127 <= x <= 126 1 |
| -32,767 <= x <= 32,766 2 |
| -2,147,483,647 <= x <= 2,147,483,646 4 |
| Floats, |
| single precision (default) 4 |
| double precision 8 |
| strings maximum length |
+-------------------------------------------------------------+"
One thing you could do, since you only have two years, is first difference data. The estimated coefficients will be the same and it will cut your data set in half.
Something like:
xi: reg diff_nrtrgain diff_nschools ... i.instid, nocon
Hope this helps,
Scott
----- Original Message -----
From: "Tim R. Sass" <[email protected]>
Date: Wednesday, July 14, 2004 12:17 pm
Subject: st: Memory Usage
> I may be crazy, but I am trying to estimate a fixed effects model
> with a
> handful of explanatory variables plus 3,100 explicit dummies on a
> two-year
> panel data set containing 1.7 million observations (about 850,000
> fixed
> effects). I am using a Sun workstation with 8GB of RAM.
>
<snip>
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
