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

st: Re: NHIS data, SVYLOGIT, and Subpopulations

From   Friedrich Huebler <>
Subject   st: Re: NHIS data, SVYLOGIT, and Subpopulations
Date   Tue, 7 Sep 2004 10:47:53 -0700 (PDT)


This is a FAQ: What do I do when one of the survey estimators returns
an error message, "stratum with only one PSU detected"?

Friedrich Huebler

--- Marisa Wilson <> wrote:
> Dear List:
> I have a perplexing dilema that someone on this list may have
> encountered before.  I am using National Health Interview Survey
> (NHIS)
> data for a secondary data analysis for my dissertation.  I need to
> run
> several logisitic regressions.  The data that I need is actually a
> subsample of the total data set (those 65 years of age and over and
> with
> at least on functional limitation).
> I have the entire data set in Stata (all 97,000 or so respondents -
> all
> ages and functional limitations).  I tried to run the first
> logistic
> regression (SVYLOGIT)  after doing SVYSET.  I put in an IF
> statement so
> that the analysis would be done on only those 65 yrs of age and
> over and
> with at least 1 functional limitation.  I get "stratum with only
> one PSU
> detected
> r(460)".  I loaded the entire data set from the go get because I
> was
> getting this error with the subpopulation.
> Any suggestions as to how I can run SVYLOGIT on only those people
> 65 +
> and with atleast on functional limitation and not get thos error?

Do you Yahoo!?
Y! Messenger - Communicate in real time. Download now.
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index