The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Countries » Ethiopia » Women Empowerment Index
Re: Women Empowerment Index [message #15006 is a reply to message #14993] Thu, 24 May 2018 17:27 Go to previous messageGo to previous message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3110
Registered: February 2013
Senior Member

Following is a response from Senior DHS Specialist, Kerry MacQuarrie:

I would recommend NOT combining these into a single "women's empowerment index" for conceptual and measurement reasons. I would recommend two separate measures.
1. The treatment of the decision-making component (v743a-v743f variables) makes a lot of sense. I would keep this as is and label it "decision-making".
2. I would combine the v744a-v744e variables into a separate "attitudes toward wife beating" measure. Two options that come to mind for creating this measure are (1) create a dichotomous variable and take acceptance of wife beating in ANY scenario (any v744 variable ==0 or ==8) as 0 and rejection of wife beating in ALL scenarios (i.e. v744a==0 & v744b==0 & v744c==0 & v744d==0 & v744e==0 ) as 1; or (2) create an additive index which sums the number of scenarios in which wife beating is accepted (==0 or ==8). In the first option, a higher value--1--indicates less acceptance of wife beating and goes in the same direction as the decision-making measure. In the second option, a higher value indicates more acceptance of wife beating and goes in the opposite direction of the decision-making measure. The first option is more common and I prefer it, but this is the analyst's choice.
 
Read Message
Read Message
Read Message
Previous Topic: Findings Inconsistency
Next Topic: Weighting and Multiple Imputation
Goto Forum:
  


Current Time: Fri Jul 12 07:27:59 Coordinated Universal Time 2024