The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » Sample weights and stratification - Nigeria 2008 and 2018
Re: Sample weights and stratification - Nigeria 2008 and 2018 [message #19288 is a reply to message #19287] Thu, 21 May 2020 05:13 Go to previous messageGo to previous message
Goethe2014 is currently offline  Goethe2014
Messages: 10
Registered: May 2020
Member
Dear Tom,
Thanks a lot for the advice.

I applied the command first to the DHS 2008 data [egen stratum_ID_2008=group(ssstate v025)].If I tabulate stratum_ID_2008 it now shows me 74 distinct values. If I do the same in the DHS 2018 data [egen stratum_ID_2018=group(ssstate v025)] this also gives me 74 distinct values.

I then appended the DHS 2018 data to the DHS 2008 data [append using "MY_DHS_2018_FILE"]. If I now order the total appended dataset [order stratum_ID_2008 stratum_ID_2018] and browse I can see that of course there is no entry (.) for the stratum_ID_2018 for observations from DHS 2008 which makes sense. If I now make use of the command you suggested [egen stratum_ID=group(stratum_ID_2008 stratum_ID_2018)]this creates missing values only as either stratum_ID_2018 is missing for DHS 2008 data and vice versa stratum_ID_2008 is missing for DHS 2018 data. Therefore the newly generated stratum_ID variable in the appended/combined dataset has 0 entries.
Did I miss something or is there any solution for this issue?

Having solved this I would now have the weights (v005) and the stratification indicator (stratum_ID). If I want to define svyset I therefore know 2 of 3 needed values [svyset [pweight==v005], psu (???) strata (stratum_ID)]. You wrote that I could not assume the clusters (which are equal to the Primary Sampling Unit/psu v021) are the same in DHS 2008 and 2018. How would therefore the complete command for syset look like?

Thanks in advance.
Greetings
 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: Pooling men, women and household DHS from Haiti
Next Topic: Weight about pooling 2003,2008,2013,2018 BR dataset in Nigeria
Goto Forum:
  


Current Time: Thu Mar 28 05:36:01 Coordinated Universal Time 2024