The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Wealth Index » Recalculating wealth index for rural subset
Recalculating wealth index for rural subset [message #967] Sun, 08 December 2013 19:09 Go to next message
user-rhs is currently offline  user-rhs
Messages: 132
Registered: December 2013
Senior Member
I am running analysis on Ethiopia for the rural subset. Since the wealth index was calculated for the entire country, I don't think it would be appropriate to use the built-in wealth index variables (v190, v191), as the the wealth index scores follows a bimodal distribution where scores for rural areas are concentrated around the lower range of the values and the scores for urban areas are concentrated around the upper range of the values. In addition, the variables used may fall on the "wealth" construct differently for urban vs. rural (reference). For this reason, I would like to recalculate the wealth index for Ethiopia for the rural subset only.

The documentation (also here) states that the variables used to create the index come from the HH questionnaire, including country-specific assets. Is there a way for me to get a list of all the variables used for Ethiopia 2011?

And a more theoretical question: if I am running the analysis on this rural subset using my recalculated wealth index score, is it still valid for me to use the built-in sample weight vbl (v005)?

Thanks
RHS
Re: Recalculating wealth index for rural subset [message #1148 is a reply to message #967] Mon, 13 January 2014 17:10 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
Here is a response from one of our experts, Dr. Shea Rutstein:

We have calculated separate wealth indexes for Ethiopia and then combined them into a composite index. The separate indexes also have separate quintiles. I am attaching the score file and the SPSS syntax. By the way, it is correct to use the weight variable.

The format for the score file:



Variable Rec Start End Format
QHCLUST 1 1 3 F3.0
QHNUMBER 1 4 6 F3.0
combscor 1 7 17 F11.5
Ncombsco 1 18 20 F3.0
URB1 1 21 31 F11.5
NURB1 1 32 34 F3.0
RUR1 1 35 45 F11.5
NRUR1 1 46 48 F3.0

RUR1 is the rural wealth score and NRUR1 is the rural wealth quintile.

If this has not answered your question adequately, please reply

Thank you!

Re: Recalculating wealth index for rural subset [message #1180 is a reply to message #1148] Fri, 17 January 2014 12:12 Go to previous messageGo to next message
user-rhs is currently offline  user-rhs
Messages: 132
Registered: December 2013
Senior Member
Thanks, Liz, this is very helpful. I have another question for you: What variable in the recode file is used to determine whether the individual is a domestic servant (variable is used in factor analysis for urban, rural, and combined)? I did not see anything in the individual, household, nor household member recode files with this information. Also, do the variables "HOUSE" and "LAND" used in factor analysis correspond to variables V745a and V745b in the individual recode file?

Thanks,
user-rhs
Re: Recalculating wealth index for rural subset [message #1181 is a reply to message #1180] Fri, 17 January 2014 12:53 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
One of our experts, Ladys Ortiz suggested checking occupational code variables. In the woman's recode file its V716 and in the Man's recode file it is MV716.

In the standard questionnaire, household members are categorized as to how they relate to the head of the household. Someone who may be a domestic servant would probably fall under code 12 not related. HV101 Relationship to head has the following codes:
Head 1
Wife or husband 2
Son/daughter 3
Son/daughter-in-law 4
Grandchild 5
Parent 6
Parent-in-law 7
Brother/sister 8
Co-spouse 9
Other relative 10
Adopted/foster child 11
Not related 12
Niece/nephew by blood 13
Niece/nephew by marriage 14
Don't know 98
Missing 99

As far as your query about "HOUSE" and "LAND" and V745a and V745b in the individual recode file, I believe that's correct, but I will check with someone to confirm?

If this has not answered your question adequately, please reply

Thank you!

[Updated on: Fri, 17 January 2014 15:16]

Report message to a moderator

Re: Recalculating wealth index for rural subset [message #12036 is a reply to message #1148] Tue, 21 March 2017 17:34 Go to previous messageGo to next message
kdiclem1 is currently offline  kdiclem1
Messages: 8
Registered: March 2017
Location: New Haven, CT
Member
I have a similar issue regarding Tanzania 2015-2016 data, where I am using a subset of the answers (only those that are rural).
My two questions are:
1. Do you have similar variables for this data set that would give a more precise picture of wealth indices amongst rural only?
2. I am using SAS- if I want to create a new dataset where I only have rural women, can the weight/cluster/strata variables be applied the same way?

Thank you!
Re: Recalculating wealth index for rural subset [message #12071 is a reply to message #12036] Sat, 25 March 2017 09:06 Go to previous message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User, A response from Dr. Shea Rutstein:
Quote:

We have a rural-specific wealth index in the standard recode for almost all the newer surveys.

Tanzania DHS 2015-16 should be one of these.
"Wealth Index Variables
HV270 The wealth index is a composite measure of a household's cumulative living standard.
The wealth index is calculated using easy-to-collect data on a household's ownership of
selected assets, such as televisions and bicycles; materials used for housing construction;
and types of water access and sanitation facilities.
Generated with a statistical procedure known as principal components analysis, the
wealth index places individual households on a continuous scale of relative wealth. DHS
separates all interviewed households into five wealth quintiles to compare the influence
of wealth on various population, health and nutrition indicators. The wealth index is
presented in the DHS Final Reports and survey datasets as a background characteristic
HV271 Wealth index factor score (5 decimals)"
If this is not what you are looking for, please post again. Thank you!
Previous Topic: Calculate wealth index for Bangladesh DHS 1999-00
Next Topic: Wealth index with pooled datasets
Goto Forum:
  


Current Time: Mon Mar 18 23:02:11 Coordinated Universal Time 2024