Dolores,
you can read about this problem in the SVY Stata Manual.
I use -idonepsu- from ssc to deal with this problem.
. ssc des idonepsu
----------------------------------------------------------------------------------------------------------
package idonepsu from http://fmwww.bc.edu/repec/bocode/i
----------------------------------------------------------------------------------------------------------
TITLE
'IDONEPSU': module for dealing with strata that have singleton PSUs
DESCRIPTION/AUTHOR(S)
idonepsu identifies strata that have only one PSU and,
optionally, merges them into the largest strata. This command
should be used with caution as the appropriate merge of strata
depends on the sample design. This utility is intended for
persons doing large secondary data analysis where they are
uncertain of the sampling strategy and are, therefore, unable to
identify the appropriate strata in which to merge. The merge is
done in accord with the method suggested by the Stata 7 manual.
Author: Joshua H. Sarver , Case Western Reserve University
Support: email [email protected]
Distribution-Date: 20010918
INSTALLATION FILES (type net install idonepsu)
idonepsu.ado
idonepsu.hlp
----------------------------------------------------------------------------------------------------------
(type -ssc install idonepsu- to install)
HTH,
Joao Lima
2010/1/29 Dolores Jiménez Rubio <[email protected]>:
> Dear statalist users,
>
> I am trying to run a multilevel modelling clustering at the individual
> level (there are several responses from 1 individual that might be
> correlated) and adjusting for complex survey data in Stata 10. The command
> I am using is:
>
> svyset province [pw = weight], strata(region) fpc(fpc)||ID, fpc(fpc2)
>
> where:
>
> SU1: province
> fpc: number of provinces within each region
>
> SU2: individual (ID)
> fpc2: number of individuals within each region
>
> I get the following error message from Stata:
>
> Note: missing standard errors because of stratum with single sampling unit.
>
> Could anyone give me some advice on this? Thank you very much in advance
>
>
>
> *
> * 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/
