The DHS Program User Forum: Geographic Data » Two Way Fixed Effects with Year and Cluster FEs

Home » Data » Geographic Data » Two Way Fixed Effects with Year and Cluster FEs (Using DHS Clusters across Surveys)

Show: Today's Messages :: Show Polls :: Message Navigator

Two Way Fixed Effects with Year and Cluster FEs [message #28798]

Sat, 09 March 2024 21:51

Joseph
Messages: 1
Registered: March 2024

Member

Hello Everyone,

The idea is to examine the effect of the distance of the centroids of DHS clusters to nearby facilities on child health. We pull the independent cross-sections together to run two-way fixed effects. However, we just read that DHS clusters are not the same across surveys, which has serious consequences for our analysis. We will be glad if anyone is willing to give any suggestions on how best to tackle this issue?

We are running high-dimensional fixed effects (reghdfe) in STATA.

Report message to a moderator

Re: Two Way Fixed Effects with Year and Cluster FEs [message #30406 is a reply to message #28798]

Sun, 24 November 2024 22:47

BrandynKunde
Messages: 1
Registered: November 2024

Member

Instead of using DHS clusters, you can switch to more stable geographic units such as districts, provinces, raft wars, or administrative regions. Combine cluster data with these administrative units for consistency.

[Updated on: Sun, 24 November 2024 22:47]

Report message to a moderator

Previous Topic:	Rwanda District identifier: 2005 and 2007-08 DHS
Next Topic:	How to Access GPS Data

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Wed Nov 27 00:32:53 Coordinated Universal Time 2024