Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: jacknife using replicate weights


From   bill magee <magee@chass.utoronto.ca>
To   statalist@hsphsun2.harvard.edu
Subject   st: jacknife using replicate weights
Date   Tue, 10 Feb 2004 10:11:41 -0500

I did something similar once. Here is an example of the way I did it, given pre-constructed weights
set to zero for those not in the (sub)sample (i.e. bootstrap or jacknike..). There is no need to use the canned programs to do this.

bill magee

#delimit ;
set more off;

gen bagespline1=0;
gen bagespline2=0;
gen bagespline3=0;
gen bagespline4=0;
gen brecentim=0;
gen bltim=0;


* svylogit separtnerx agespline1 agespline2 agespline3 agespline4
recentim ltim ;

for var w14-w1000: svyset [pweight=X]\
svylogit separtnerx agespline1 agespline2 agespline3 agespline4
recentim ltim
if X~=0\
replace bagespline1 = _b[agespline1] if _b[agespline1] ~=. \
replace bagespline2 = _b[agespline2] if _b[agespline2] ~=. \
replace bagespline3 = _b[agespline3] if _b[agespline3] ~=. \
replace bagespline4 = _b[agespline4] if _b[agespline4] ~=. \
replace brecentim = _b[recentim] if _b[recentim] ~=. \
replace bltim = _b[ltim] if _b[ltim] ~=. \


outfile bagespline1
bagespline2
bagespline3
bagespline4
brecentim
bltim
using mX in 1 ;

clear;

Date: Mon, 9 Feb 2004 17:33:36 -0500
From: "Clayman, Marla (NIH/NCI)" <claymanm@mail.nih.gov>
Subject: st: jknife using replicate weights

This message is in MIME format. Since your mail reader does not understand
this format, some or all of this message may not be legible.

- ------_=_NextPart_001_01C3EF5C.57F20415
Content-Type: text/plain

I'd like to run analyses using jackknife estimation. My dataset has a
frequency weight and replicate weights (50) to be used in the jknife
command. Stata does not seem to allow for specifying use of these weights.
Can anyone help me with the syntax, or does Stata really not allow that?

Also, is there a way to get Stata to allow the use of non-integer frequency
weights?

Thanks,

Marla Clayamn

*
* 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/




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