Re: st: survey analysis : three-way table and use of "subpop"

[Steven Samuels <sjsamuels@gmail.com>]

One more time: make that "col"!

Steve

To get disease prevalence,  I should have added the "row" option to the -svy: tab- commands. This is corrected below.

S.

<redacted>-

Simplest is to use -svy: prop-

**************************************************
svy: prop Diseased, over(Age Gender Race)
*************************************************

The results list categories like _subpop_1, _subpop_2, but show a legend so that you know what is what.  

If prevalence is low, a lower confidence interval endpoint could fall below zero. In that case, you should use four instances of -svy: tab-, because -svy: tab- computes confidence intervals for the logit of a proportion, then transforms back.

e.g.
******************************************************
svy, subpop(if Gender==0 & Race==0): tab Diseased Race, col
svy, subpop(if Gender==0 & Race==1): tab Diseased Race, col
etc.
******************************************************

Steve


On Sep 20, 2011, at 11:55 PM, <redacted> wrote:

Hi, I need help with svy analysis. I have 4 variables:

1) Diseased: yes=1 old=0
2) Gender: male=1 female=0
3) Age: young=1 old=0
4) Race: Malay=1 non-Malay=0

My svy command is :
Svyset ebid [weight=weight4], strata(strata) fpc(fpc)


Question:
I want to produce this table.  This table looks like a three-way table.

==============================================================
	              Prevalence	                          Prevalence
	                  Male	                           Female
           	Malay	Mon malay	Malay	Non malay
Agegp

-young

-old 				
				
==============================================================

In a normal tabulate command, I can use "bysort gender: tabulate  race age"

but in svy command, how can I do this? Should I use “subpop” command,
one time for male and the other time for female? will that be valid?
Are there any other options?

Svy, subpop(?): tab race age diseased



*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/