Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: rolling regression calculation speed and large data sets


From   Malcolm Wardlaw <malcolm@mail.utexas.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: rolling regression calculation speed and large data sets
Date   Fri, 03 Oct 2008 12:47:06 -0500

Thanks for the reply.  It's not really the question I was asking, but I
really like what you did.  I think it solves my immediate problem in an
oblique way, so thank you.  That's pretty slick, I must say.   I think I
often get so used to typing in "reg y x" that I forget how easy it is
just to calculate simple linear regression output manually.  I think
I'll expand a program like this for my permanent files.

I haven't heard from anyone who knows about how the memory schema works,
but I was wondering if there are any written resources on this.  Does
NC152 handle this at all?

"Austin Nichols" <austinnichols@gmail.com
<mailto:austinnichols@gmail.com>>" wrote:

>The described phenomenon seems odd to me, and worth some further
>investigation, but have you considered generating those variables
>using lag operators (h tsvarlist) and a by: prefix instead of looping
>over obs and running regressions?  That approach would have the added
>advantage of ensuring you are not tripped up by any missing time
>periods, assuming you have -tsset- properly (e.g. if some company 36
>obs in a row are not for 36 consecutive trading days but for 50, say,
>because of missing obs).



*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index