Mandy,
just do this
*******
use http://www.ats.ucla.edu/stat/stata/notes/hsb2, clear
svyset [pw=socst], strata(ses)
svy:mean read write
lincom read-write
********
. svy:mean read write
(running mean on estimation sample)
Survey: Mean estimation
Number of strata = 3 Number of obs = 200
Number of PSUs = 200 Population size = 10481
Design df = 197
--------------------------------------------------------------
| Linearized
| Mean Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
read | 53.52886 .7118855 52.12497 54.93276
write | 53.94352 .6205423 52.71976 55.16728
--------------------------------------------------------------
. lincom read-write
( 1) read - write = 0
------------------------------------------------------------------------------
| Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
(1) | -.4146551 .6194956 -0.67 0.504 -1.636349 .8070392
------------------------------------------------------------------------------
HTH,
Joao Lima
2009/8/18 Mandy fu <[email protected]>:
> Hi all,
>
> Previous discussion of comparing means in survey data are focus on two
> groups. I am interested in comparing means of two variables in survey
> data.
>
> For example, in the following data set for students test scores, I'd
> like to compare the population means of "read" and "write". I was
> wondering , since the probability weight for each student is constant,
> if it is fine that I just use t test? If I need to use probability
> weight, how to do that after the survey mean estimation?
>
> I tried --svy:mean-- and then use--lincom--. But since there seems
> always some errors message.
> ---------------------------------------------
> use http://www.ats.ucla.edu/stat/stata/notes/hsb2, clear
> svyset [pw=socst], strata(ses)
> *** t test
> ttest read=write
> ***svy and lincom
> svy:mean read
> matrix B=e(b)
> svmat B
> svy:mean write
> matrix C=e(b)
> svmat C
> lincom B C
> **regressor B1 not found
> **r(111);
> ------------------------------------
> Thanks for your help!
>
> Mandy
> *
> * 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/
>
--
----------------------------------------
Joao Ricardo Lima, D.Sc.
Professor
UFPB-CCA-DCFS
Fone: +5538387264913
Skype: joao_ricardo_lima
----------------------------------------
*
* 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/
