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: svyselmlog - singleton cluster detected
From
Nick Cox <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
RE: st: svyselmlog - singleton cluster detected
Date
Thu, 31 Mar 2011 18:51:41 +0100
It seems, as one would guess, that -svyselmlog- gets its information on PSUs from what has been -svyset-. I can't add more.
Nick
[email protected]
Murod Aliyev
Dear Nick,
Sorry for forgetting to specify the source. Yes, -svyselmlog- is from SSC.
No, I do not use if or in. I use entire sample as checked through svydes.
Many thanks!
Dear Joao,
Many thanks for the advice. I tried to do what you suggested - to drop
single observations in a PSU. -svyselmlog then worked, but without
bootsrapping. If boostrapping option is specified then after two three
resamplings it returns "conformability error". Any advice on this error?
Many thanks!
----- Original Message ----
From: Joao Ricardo F. Lima <[email protected]>
To: [email protected]
Sent: Thu, 31 March, 2011 14:34:54
Subject: Re: st: svyselmlog - singleton cluster detected
Nick is right here.
You must have variables with missing values, the var_dep of the main equation.
You can do the -svydes var_dep, single- and see if there are stratum
with a singleton
PSU, correct (if exists) and run the -svyselmlog-.
Joao Lima
2011/3/31 Nick Cox <[email protected]>:
> -svyselmlog- is from SSC. Please remember to specify where
> user-written commands you refer to come from.
>
> Are you issuing any -if- or -in- restrictions? Are there missing
> values in any of those variables? Those are possible ways in which
> -svyselmlog- might see fewer observations than -svydes-.
>
> Nick
>
> On Thu, Mar 31, 2011 at 1:59 PM, Murod Aliyev <[email protected]> wrote:
>
>> I am using svyselmlog to estimate consumption levels for employees of
>different
>> categories: wage, self-employed, entrepreneurs, unemployed. Data are from
>> stratified survey. However, svyselmlog returns an error message “singleton
>> cluster detected”. svydes command does not reveal any stratum with a
singleton
>> PSU. Therefore, I am stuck as I do not understand the reason for the error
>> message to appear and I do not know how to solve the problem.
*
* 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/