Tabout with svy - balanced repeated replication variance estimation

[Jana Hirschtick]

Hi everyone,

I am analyzing a complex survey (Population Assessment of Tobacco & Health) and need to use Balance Repeated Replication (BRR) for the variance estimation. I am generating hundreds of tables and would like to use some automated procedure (tabout or putexcel) to help populate the tables. However, when I run the tabout command that works for a colleague (his dataset calls for Taylor Series Linearization) it only spits out the point estimates, not the standard errors. When I use Taylor Series instead it does spit out the SEs, but they are wider than they should be (hence the need to use BRR). Is there a way to use tabout with BRR? Here is a snippet of code:

svyset [pweight= R01_A_PWGT], brr(R01_A_PWGT1 - R01_A_PWGT100) vce(brr) mse fay(.3)

tabout both UM_W1_A_cigs_everysome_menthol_1 using "PATH_1.txt", ///
replace f(1p) c(row lb ub) layout(col) svy per npos(col) nlab(Observaciones) ///
h2(" Prevalence of Menthol use in PATH W1") ///
clab(SE) h1(nil)cibnone ci2col h3(|nonsmokers%|lb|ub|menthol%|lb|ub|nonmenthol%|l b|ub|unknown%|lb|ub|total|observations) cisep(" ")

Thanks in advance,
Jana

[bfairman]

Hi,

I am also working with the PATH data and am experiencing the same problem of tabout not outputting CI using BRR. However, I have been able to get tabout to produce SE under BRR. I can only assume that there must be an error in tabout that prevents output of CI using BRR.

One solution you might try that is currently unavailable to me is to make sure Stata is using the current version 2 (2.0.8) or try beta version 3 (http://ianwatson.com.au/stata.html) to see if this problem as already been solved. If not, then I'd recommend altering the author of tabout to this problem.

Good luck,
Brian

[David Radwin]

Does Stata produce standard errors when you use a built-in command like the following? If not, maybe the problem is unrelated to tabout.

svy: tab both UM_W1_A_cigs_everysome_menthol_1