The DHS Program User Forum: Dataset use (other programs) » R DHS aggregation by Indigenous Identity in Guatemala

Home » Data » Dataset use (other programs) » R DHS aggregation by Indigenous Identity in Guatemala (Aggregate health statisitics by indigenous group)

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

R DHS aggregation by Indigenous Identity in Guatemala [message #24063]

Tue, 15 February 2022 14:52

hmwoods02
Messages: 2
Registered: February 2022

Member

Hello,

I am trying to use DHS data in R to create health data that is broken down by tribal group in Guatemala. I have identified variable SETID (self identification), s114 (language learned to speak) or s117(languages spoken at home) as relevant for identifying indigenous identity, however I am not sure how to construct such a conplex variable in R. There are 25 indigenous groups identified in the data.

Thanks

Report message to a moderator

Re: R DHS aggregation by Indigenous Identity in Guatemala [message #24084 is a reply to message #24063]

Mon, 21 February 2022 08:37

Bridgette-DHS
Messages: 3230
Registered: February 2013

Senior Member

Following is a response from DHS Senior Sampling Specialist, Mahmoud Elkasabi:

You can try the following function to group the variables into one variable (tribalg).

GUBR71 <- GUBR71 %>% 
               mutate(tribalg = group_indices(., setid, s114))

Report message to a moderator

Previous Topic:	alternative to exporting with xlsx
Next Topic:	Respondent's sex NFHS-5

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Sat Jul 5 20:39:17 Coordinated Universal Time 2025