The DHS Program User Forum: Geographic Data » Sample Weights in Geographically Weighted Regression

Home » Data » Geographic Data » Sample Weights in Geographically Weighted Regression

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

Sample Weights in Geographically Weighted Regression [message #13935]

Fri, 26 January 2018 10:48

mcarrel
Messages: 2
Registered: November 2017

Member

I would like to use geographically weighted regression techniques to understand how the relationship between covariates and outcomes in the Kenya DHS vary over space (i.e. is the relationship between wealth and health care usage different across clusters). Geographically weighted regression can be done in R but not SAS or Stata and doesn't have built in commands for applying sample weights, only spatial weights. Is there a way to multiply the sample weight by all the covariates and the dependent variable and then incorporate this new, already weighted, data into the geographically weighted regression environment?

Report message to a moderator

Re: Sample Weights in Geographically Weighted Regression [message #14073 is a reply to message #13935]

Fri, 09 February 2018 11:47

Bridgette-DHS
Messages: 3199
Registered: February 2013

Senior Member

Following is a response from Senior DHS Stata Specialist, Tom Pullum:

Your question goes beyond the kind of analysis that we conduct within DHS. We hope that other users of the forum may be able to offer suggestions.

Report message to a moderator

Previous Topic:	Spatial Data Repository Geospatial Covariates
Next Topic:	cluster-level data for spatially modeled map surfaces for recent population-based survey

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Sat Nov 23 09:13:26 Coordinated Universal Time 2024