It is usually easier to make a diagnosis of the problem if you show what you
actually typed. With the default number of lags (1 2) and 18 variables the
matsize would need to be at least 667 (see example below), given the number
of parameters to estimate. Perhaps you are using more than 2 lags?
Scott
. clear
. set obs 1000
obs was 0, now 1000
.
. forv i = 1/18 {
2. gen x`i' = uniform()
3. }
.
. gen time = _n
. tsset time
time variable: time, 1 to 1000
. set matsize 667
Current memory allocation
current memory usage
settable value description (1M = 1024k)
--------------------------------------------------------------------
set maxvar 5000 max. variables allowed 1.733M
set memory 10M max. data space 10.000M
set matsize 667 max. RHS vars in models 3.450M
-----------
15.183M
. var x*
Vector autoregression
Sample: 3 1000 No. of obs = 998
<snip>
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Theodorou, C.
> Sent: Wednesday, August 03, 2005 12:30 PM
> To: [email protected]
> Subject: st: VAR with 18 variables and problem with the mat size
>
>
> i am trying to run a var model with 18 variables but the mat size keeps
> coming up as too small. the university uses the intercooled version of
> stata and only has mat size max 800. even with 800 it will still say mat
> size too small
>
> what do i do? what is the problem?
>
>
> thank you
>
> best regards
> costas
> uni of leicester
> dept of economics
>
*
* 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/
