|
|
|
||||
|
|
|||||
* svy commands are set up differently in Stata 9 than in Stata 7 or 8 use http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_intro/oscs1, clear * Stata 8 svyset * svyset [pweight=pw], psu(dnum) fpc(fpc) * svyregress api00 awards meals * Stata 9 svyset - note that the psu is now listed before the pweigh svyset dnum [pweight = pw], fpc(fpc) svy: regress api00 awards meals * can use tabulate with only one variable (one-way tables) svy: tab yr_rnd svy: tab yr_rnd both clear * Stata 9 handles BRR and jackknife replicate weights. * use of jackknife replicate weights set mem 10m
use http://www.ats.ucla.edu/stat/stata/seminars/stata9/nhanes2clean, clear svyset [pweight = finalwgt], jkrweight(jkw_1 - jkw_62, multiplier(.5)) vce(jackknife) svy: regress weight height * deff and meff are now part of the postestimation commands and not given with the standard output estat effects estat effects, meff meft * Stata 9 handles poststratification * need to supply the poststratification variable and the poststatification weight * subpop svy, subpop(rural): mean weight svy: mean weight, over(sex) svy: mean weight, over(race sex)
UCLA Researchers are invited to our Statistical Consulting Services
We recommend others to our list of Other Resources for Statistical Computing Help
These pages are Copyrighted (c) by UCLA Academic Technology Services