Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Clustered errors without saving data in pagefile
From
v van kervel <[email protected]>
To
[email protected]
Subject
st: Clustered errors without saving data in pagefile
Date
Sat, 24 Sep 2011 12:18:33 -0700 (PDT)
Dear Statalist,
I have a 25Gb dataset. A simple regression (regress) takes about 15 seconds
to run. However, when I specify clustered (or robust/ newey west) SEs, it
takes 1,5 hours.
I believe the reason is that first the data in memory is copied to the
harddisk in a temporary pagefile, then the robust SEs are calculated and
saved, and finally the dataset is read into memory again. This is extremely
time consuming.
My question: Can I obtain clustered errors without copying the data in
memory to the hard disk?
I have 40Gb Ram memory, so I expect this is enough space to do the
calculations in Ram memory only.
Thank you,
V van Kervel
--
View this message in context: http://statalist.1588530.n2.nabble.com/Clustered-errors-without-saving-data-in-pagefile-tp6827732p6827732.html
Sent from the Statalist mailing list archive at Nabble.com.
*
* 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/