The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Weighting data » Weighting district-level data
Re: Weighting district-level data [message #8798 is a reply to message #8793] Sat, 19 December 2015 06:11 Go to previous messageGo to previous message
amira.elshal.1@city.ac.uk is currently offline  amira.elshal.1@city.ac.uk
Messages: 52
Registered: April 2013
Senior Member
1- In my case, a district has more than one PSU. But given that the numerator/denominator cancel each other out, how can I weigh my data? And shall I cluster when I regress afterwards (as you have taught me in your comment number 3)? You pointed out that "Clustering might not work here at all".

Note: I use bootstrapped standard errors in the second stage when I regress.

3- You are right. When I delete the extra "," after p(t), the model run. Thank you!

4- I do not know for sure the number of PSUs per district (probably around 2-6 PSUs). But I know that each district has a reasonable number of clusters, not just one cluster.
 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: Collection of Strata Information
Next Topic: Descriptives and chisq
Goto Forum:
  


Current Time: Thu Dec 5 11:43:27 Coordinated Universal Time 2024