s-news
[Top] [All Lists]

subpopulation in survey library

To: s-plus news <s-news@lists.biostat.wustl.edu>
Subject: subpopulation in survey library
From: jose Bartolomei <surfprjab@hotmail.com>
Date: Tue, 8 Jul 2008 14:31:30 +0000
Importance: Normal
In-reply-to: <41B789B34AE64A469F17DC2C9AE5608F0162D493@mailbe01.mc.vanderbilt.edu>
References: <41B789B34AE64A469F17DC2C9AE5608F0162D493@mailbe01.mc.vanderbilt.edu>

Dear S+/R users:

 

 

I’m still conducting analysis using the survey package, to estimate the prevalence & SE of lifetime asthma (ASTHMA2) and current asthma (ASTHNOW) in complex survey design (stratify design). 

 

I have problems estimating the standard errors when the procedures is implemented in a subpopulation of the entire universe.

 

The procedure goes as follows:

 

 

BRFSS.05.svy<-svydesign(ids=~0, strata=~STSTR, weights=~FINALWT, data="">

 

BRFSS.05.svy<-as.svydesign2(BRFSS.05.svy)

 

svymean(~ASTHMA2,design=BRFSS.05.svy)

              mean     SE

ASTHMA21 0.1928144 0.0082

ASTHMA22 0.8061478 0.0082

ASTHMA27 0.0010377 0.0005

 

; which gives the correct prevalence and standard error estimators.

 

Then want to calculate the current prevalence, which is a subpopulation of ASTHMA2.

 

I use the following procedure

 

 

Nw.05<-sum(BRFSS.05.F$FINALWT)# the weighted population

 

AnowPrev<-(svytotal(~ASTHNOW, design=BRFSS.05.svy2, na.rm=TRUE)/Nw.05)*100

 

> test

             total      SE

ASTHNOW1  8.792641 15761.4

ASTHNOW2 10.456593 19130.4

ASTHNOW7  0.032211   664.2

 

Or

  

subtest.optB<-subset(BRFSS.05.svy2, ASTHNOW==1)

(svytotal(~ASTHNOW, subtest)/Nw.05)*100

 

Total      SE

ASTHNOW1  8.792641 15761.4

ASTHNOW2 10.456593 19130.4

ASTHNOW7  0.032211   664.2

 

; which gives the correct prevalence but incorrect standard error estimators.

 

How can I get the correct SE’s?

 

Thanks in advance

 

 

Jose

 PS: Bellow are 2 examples of various procedures that I tried that give incorrect results.

> svymean(~ASTHNOW, design=BRFSS.05.svy2)

         mean SE

ASTHNOW1   NA NA

ASTHNOW2   NA NA

ASTHNOW7   NA NA

 

 

> svymean(~ASTHNOW, design=BRFSS.05.svy2, na.rm=TRUE)

              mean     SE

ASTHNOW1 0.4560157 0.0231

ASTHNOW2 0.5423138 0.0231

ASTHNOW7 0.0016706 0.0012

 

 



Making the world a better place one message at a time. Check out the i’m Talkathon.
<Prev in Thread] Current Thread [Next in Thread>