Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RE: When to use stdize and stdweight with svy: tab and svy: mean?
From
Arturo Rodriguez <[email protected]>
To
[email protected]
Subject
Re: st: RE: When to use stdize and stdweight with svy: tab and svy: mean?
Date
Fri, 18 Nov 2011 15:26:49 -0600
Thanks Shaun!
Would using the command you suggest __ svy: tab dummy district,
stdize(age) stdweight(varX) __ be equivalent to specifying
post-stratification weights and then using the svy: tab without the
stdsize and stdweight?
i.e.
svyset villages [pweight = pw] strata(health_center)
fpc(total_number_of_villages_per_hc) poststrata(age) psw(varX)
svy: tab tab dummy district
Thanks!
Arturo
On Fri, Nov 18, 2011 at 4:43 AM, Scholes, Shaun <[email protected]> wrote:
> Hi Arturo, I think the short answer is that the stdize and stdweight options are only needed if you are interested in direct standardisation. If not, then svy:tab dummy district will be sufficient for your purposes.
>
> i) Your variable health_center is the sampling strata (and so is declared in the svyset command) - as is the sampling weight (pw).
> ii) You may (as I often do) want to adjust the sampling weight to ensure the same age distribution across groups. This would make age the standard strata; and stdweight would be a variable (call it varX) that would contain the population sizes in each age group.
>
> So then you would use:
>
> svy: tab dummy district, stdize(age) stdweight(varX)
>
> Hope this helps
> Shaun
>
>
>
>
>
>
>
>
>
>
>
>
>
> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On Behalf Of Arturo Rodriguez
> Sent: 17 November 2011 23:05
> To: [email protected]
> Subject: st: When to use stdize and stdweight with svy: tab and svy: mean?
>
> Hi everybody,
>
> I am working with survey data which was collected through a one-stage cluster sample with stratification. I am trying to tabulate two variables -a dummy and a categorical variable identifying districts. I noticed that I can do the tabulation either by using "svy: tab dummy district" or by "svy: tab dummy district, sdize(strata_var) stdweight(weight_var)". I ran both commands and see that the % in the results change from one command to the other; however, I don't know what is happening behind the scenes.
>
> My sample was stratified (by health centers) and the primary sampling unit were "villages". In defining my survey characteristics I used the
> command:
> svyset villages [pweight = pw] strata(health_center)
> fpc(total_number_of_villages_per_hc)
>
> What is the difference between the results I'm getting from each option?
> (1) svy: tab dummy district
> (2) svy: tab dummy district, stdize(health_centre) stdweight(pw)
>
> Since I'm working with stratified cluster data, does that necessarily mean that all my svy: tab and svy: mean commands need to specify the stdize and stdweight options?
>
> Thanks in advance for all the wisdom.
>
> Arturo
> *
> * 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/
>
>
>
> *
> * 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/
>
--
Arturo Rodríguez
M.A. in International Development Economics
mobile: +52 (155) 8598 3608
email: [email protected]
skype: arturo_aus
twitter: @ArturoRT
*
* 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/