how to extract weighted data in "survey" package
Thank You Anthony for the message. Why did not I get the same values in the following examples? To get the adjusted value, should not we just multiphy by weight? For example, I multiplied "api00" by "column "pw" (mean(apistrat$api00*apistrat$pw/100)) but I did not get the same value as of survey package given. I think I did mistake. Any suggestions? # load the survey library library(survey) # load the apistrat data.frame data(api) # look at the first six records head(apistrat) # look at the weight column only apistrat$pw # calcualet mean using raw data and afetr adjusted svymean(~api00, dstrat) mean(apistrat$api00*apistrat$pw/100)
From: Anthony Damico <ajdamico at gmail.com>
Sent: January 1, 2017 8:00 AM
To: Kristi Glover
Cc: R-help
Subject: Re: [R] how to extract weighted data in "survey" package
Sent: January 1, 2017 8:00 AM
To: Kristi Glover
Cc: R-help
Subject: Re: [R] how to extract weighted data in "survey" package
# load the survey library
library(survey)
# load the apistrat data.frame
data(api)
# look at the first six records
head(apistrat)
# look at the weight column only
apistrat$pw
On Sun, Jan 1, 2017 at 9:49 AM, Kristi Glover <kristi.glover at hotmail.com<mailto:kristi.glover at hotmail.com>> wrote:
Hi R Users,
Happy New Year
I wanted to see the data after raw data was adjusted/weighted but I could not get it. Any suggestions?
I would like to see which data points got more weight after the design was used.
I have given you an example what I tried but I was not successful .
Thanks
library(survey)
data(api)
rawData<-data.frame(API00=apistrat$api00, API99=apistrat$api99)
head(rawData)
dstrat<-svydesign(id=~1,strata=~stype, weights=~pw, data=apistrat, fpc=~fpc)
svyplot(api00~api99, design=dstrat, style="bubble")
adjustedData<-data.frame(API00=(~api00, design=dstrat),API99=(~api99, design=dstrat ))
head(adjustedData)
[[alternative HTML version deleted]]
______________________________________________
R-help at r-project.org<mailto:R-help at r-project.org> mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.