Re: st: svyset

[Rebecca Pietrelli <rebecca.pietrelli@gmail.com>]

Dear Steve and Stas,

first of all, thank you very much for your time and suggestions.

- The purpose of my analysis is to describe aspects of population of
Uganda, related to remittances of migrants, starting from a survey of
2000 households.
For example, estimation of the total number of hhs that receive
remittances; the total number of times in 12 months hhs receive
remittances; the total amount of remittances received in cash and
kind, and so on.
Basically, by using the commands: svy: total and avy: mean.

- In this web page, they suggest to use fpc with systematic sampling:

 http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_8/default.htm

- Regarding the discrepancies in the number of PSUs; I have different
number, for example, in the file that collects variables about
remittances from household members (PSUs=191) and in the file that
collects the same variables about remittances from friends (PSUs=197).
This may suggests that in some PSUs, hhs that receive remittances from
household members were not sampled.
For sure, when the number of PSUs exceeds the number of PSUs of the
report (200) there is some problem of recording.

Thank you again
Best,
Rebecca








2012/11/3 Steve Samuels <sjsamuels@gmail.com>:
>
> We didn't answer Rebecca's original question about the number of PSUs:
>
> "
>>  I noticed that units = 191 instead of 200 (as
>> in the survey report) in one file of the dataset and units = 209 in
>> another file of the datset.
>>
>> Are these differences plausible or not?\
>
>
> The discrepancies are disturbing. I can think of several reasons why the
> file difference might occur, including a miscoding or renaming of PSU.
> If you have access to the "other" file, you might check if the number of
> respondents is the same. I'm not sure what you mean about "another file
> of the dataset"; do you mean another "copy"? A file with different
> variables? In any case, one way to solve this mystery is to write to the
> study authors.
>
> Steve
>
>> From    Rebecca Pietrelli <rebecca.pietrelli@gmail.com>
>> To      statalist@hsphsun2.harvard.edu
>> Subject         st: svyset command
>> Date    Wed, 31 Oct 2012 13:07:22 +0100
>>
>> Hi,
>>
>> I am using the Stata command svyset in order to declare the survey
>> design for my dataset.
>> (Uanda Migration Housolds Survey 2010).
>>
>> The sample design is two-stage stratified: in the first stage
>> enumeration areas -ea (psus) were selected, separately for rural and
>> urban areas, and in the second stage households were selected in each
>> ea, using a systematic procedure (4 hhs with international migrants, 3
>> with internal migrants and 3 without migrants).
>>
>> I used the following command:
>> svyset psu_var [pw=hhweights_var], strata(strata_var)
>>
>> and then (using svydes) I noticed that units = 191 instead of 200 (as
>> in the survey report) in one file of the dataset and units = 209 in
>> another file of the datset.
>>
>> Are these differences plausible or not?
>> Or do they mean that I wrong the svyset command?
>> I am not sure if the first stage is with or without replacement (It is
>> not mentioned in the report).
>>
>> Thank you very much for any help.
>> Rebecca
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/