Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: is svy the way to go?

From   ann e fitzmaurice <>
Subject   st: is svy the way to go?
Date   Wed, 20 Nov 2002 09:19:08 -0500 (EST)


i have a large data set where the respondendent (woman) was asked 
about her siblings)

i am looking at the siblings so have rearranged the data set from 
wide to long- each line now represents the sibling of the 

There is a grouping variable for the sibling, alive, dad of cause 
'a', dead not of cause'a'

What i would like to do is to do a crosstabl of the grouping 
variable by a second variable , e.g type of education (3 or 4 
levels), but to adjust the analysis for the fact that where the 
respondent had more brothers or sisters  there is duplication 
(overcounting) in the two crosstab variables

i would like to hear whether the use of the svy commands is the way 
to go , especially the use of svytab, the data also has to be 
weighted but i have the weighting variable.  If svy is the way to 
go, how do i account for the multiple counting, the number of times 
a sibling can appear ranges from 1 to 15 - i have a variable which 
tells me the number of times a record will appear in the data set,

id	gp	variable
1	1	1
1	1	1
2	3 	2
3	2	2
3	2	2
3	2	2

in the above example the first respondent (id =1) has two 
brothers/sisters and the second respondent (id=2) only has one 
brother / sister



ann e fitzmaurice
medical statistician
dugald baird centre
department of obs and gynae
university of aberdeen
tel 01224 553876 (direct)
fax 01224 404925

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index