The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Service Provision Assessment (SPA) » SPA multilevel analysis
SPA multilevel analysis [message #19388] Tue, 09 June 2020 10:17
Lucia is currently offline  Lucia
Messages: 2
Registered: April 2020
Member
Hello,

I am trying to run a multilevel mixed-effect logistic regression using the Kenya SPA dataset of 2010 to identify the determinants of hand hygiene during delivery services. I am focussing on the MCHIP survey and I saw that in some cases more than one delivery was observed for a single provider and more than one provider for each facility. I would like to run a two level analysis accounting for provider and facility.
I have a question concerning weights. I am using melogit and I know I should have a weight for each level. Should I use the facility weight for the facility level and the client weight for the provider?

thank you,
kind regards
Lucia
Previous Topic: Kenya SPA- weights
Goto Forum:
  


Current Time: Tue Jul 14 03:06:41 Eastern Daylight Time 2020