TY - JOUR
ID - st0187
A1 - Kolenikov, S.
TI - Resampling variance estimation for complex survey data
JF - Stata Journal
PB - Stata Press
CY - College Station, TX
Y1 - 2010
VL - 10
IS - 2
SP - 165
EP - 199
KW - bsweights
KW - balanced repeated replication
KW - balanced bootstrap
KW - bootstrap
KW - complex survey data
KW - Hadamard matrix
KW - half-samples
KW - jackknife
KW - resampling
KW - weighted bootstrap
KW - mean bootstrap
UR - http://www.stata-journal.com/article.html?article=st0187
L1 - http://www.stata-journal.com/sjpdf.html?article=st0187
AB - In this article, I discuss the main approaches to resampling variance estimation
in complex survey data: balanced repeated replication, the jackknife, and
the bootstrap. Balanced repeated replication and the jackknife are implemented
in the Stata svy suite. The bootstrap for complex survey data is implemented by
the bsweights command. I describe this command and provide working examples.
Editors note. This article was submitted and accepted before the
new svy bootstrap prefix was made available in the Stata 11.1 update.
The variance estimation method implemented in the new svy bootstrap prefix is
equivalent to the one in bs4rw. The only real difference is syntax. For
example,
. bs4rw, rw(bw*): logistic highbp height weight age female [pw=finalwgt]
is equivalent to
. svyset [pw=finalwgt], vce(bootstrap) bsrweight(bw*)
. svy: logistic highbp height weight age female
Similarly, the example using mean bootstrap replicate weights,
. local mean2fay = 1-sqrt(1/10)
. svyset [pw=finalwgt], vce(brr) brrweight(bw*) fay(`mean2fay´)
. svy: logistic highbp height weight age female
is equivalent to
. svyset [pw=finalwgt], vce(bootstrap) bsrweight(bw*) bsn(10)
. svy: logistic highbp height weight age female
The weights created by the bsweights command discussed in this article are
equally applicable with the bs4rw command and with the new vce(bootstrap)
and bsrweight() options of svy and svyset.
ER -