Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: Multistage sampling svyset

From   <>
To   <>
Subject   RE: st: Multistage sampling svyset
Date   Thu, 10 Jun 2010 17:05:10 -0230

Hi Michael,

Sorry my bad.  Whenever I estimate the proportion (using svy: prop) the
confidence intervals around the estimates are not created regardless of
the ailment.

I did a double check and there are not missing values in any communities
with respect to the ailments.  Some communities with a low sampling
number have a prevalence of 0%.  All ailments are coded as dichotomous.

I haven't experimented with the -singleunit()- option yet.  I will try


-----Original Message-----
[] On Behalf Of Michael I.
Sent: June 10, 2010 4:39 PM
Subject: Re: st: Multistage sampling svyset


You said you had this problem "when I'm trying to estimate the
proportion of study with CERTAIN ailments." [my emphasis] Does that mean
you don't have this problem with other ailments?

You said 'The message that is given is "Note: missing standard errors
because of stratum with single sampling unit."' Have you checked to be
sure that all strata (communities) have at least two non-missing
responses for each ailment? Have you experimented with the
-singleunit()- option to -svyset-?


*   For searches and help try:

*   For searches and help try:

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