Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: my SVY JACKKNIFE is very slow


From   "CONTRERAS GONZALEZ JOSE ANTONIO" <[email protected]>
To   <[email protected]>
Subject   st: my SVY JACKKNIFE is very slow
Date   Thu, 11 Jun 2009 16:10:13 -0500

I got a 3.20 ghz pc with 1015mb ram and a lot of hdd

I use a .RAW file with the obs.
To modify the data settings I use the next line

svyset zupm [pweight=fexp], strata(zest) vce(jackknife)

but the process is very slow, I can count dot by dot for each
replication, until it finish with the 1546 reps.

I do the same with the linearized method, and it is realy fast, as you
say, it takes around 8 sec. to finish.

Any suggestion?

Thanks


-----Mensaje original-----
De: [email protected]
[mailto:[email protected]] En nombre de Martin Weiss
Enviado el: Jueves, 11 de Junio de 2009 03:35 p.m.
Para: [email protected]
Asunto: st: Re: my SVY JACKKNIFE is very slow

<>

This takes around 17 seconds on my computer, so yours might be old and
slow?

***
webuse highschool, clear
//approx. 42000 obs
expand 11
d, s
svy jackknife: total weight
***


HTH
Martin
_______________________
----- Original Message ----- 
From: "CONTRERAS GONZALEZ JOSE ANTONIO" <[email protected]>
To: <[email protected]>
Sent: Thursday, June 11, 2009 10:27 PM
Subject: st: my SVY JACKKNIFE is very slow


>I am running this command
>
> svy jackknife : total p14
>
> with 42000 records and it takes several minutes to accomplish the
task.
>
> What am I doing wrong?
>
> *
> *   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/
> 

*
*   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/

*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index