The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » Child Health » weighting child data
weighting child data [message #13756] Tue, 19 December 2017 16:18 Go to next message
slolib86 is currently offline  slolib86
Messages: 3
Registered: December 2017
Location: Peru
Member
Dear all,

I going to investigate factors associated with child height (zscore variable). My main concern is about weights. I read in other messages of the forum, that we have to weight the child data (krfile) using the v005 variable. However, the v005 variable comes from the mother data (irfile) where all the data is unique per caseid variable.

I would like to know if there any problem weighting the child data(krfile) since some values of the v005 variable are repeated per caseid.

Thank you so much for your response
Re: weighting child data [message #13776 is a reply to message #13756] Thu, 21 December 2017 09:59 Go to previous messageGo to next message
Liz-DHS
Messages: 1351
Registered: February 2013
Senior Member
A response from senior sampling expert, Dr. Ruilin Ren:
Quote:

Regarding the weight variable used for analyzing the child weight, it is depending on the background. If you take only the children living with an interviewed mother, it is better to use the variable V005, the child's mother's weight. If you take all children measured in the household, it is better to use the household weight HV005. Regarding the repeated values of the weight variable (either HV005 or V005), note that the weight is a cluster level weight in DHS surveys, all HH in the same cluster share the same weight; all women in the same cluster share the same weight. So this is not a concern.
Thanks
Ruilin

Re: weighting child data [message #13845 is a reply to message #13776] Thu, 11 January 2018 14:31 Go to previous messageGo to next message
slolib86 is currently offline  slolib86
Messages: 3
Registered: December 2017
Location: Peru
Member
Thank you for your response Dr. Ruilin Ren

I have two more questions regarding weights. I am pooling DHS surveys , two surveys per country. The country I selected is Perú. I read that before to run a regression model, I should re-normalize the weights.

I proceed like previous post suggestion:

V005*=V005×(total females age 15-49 in the country at the time of the survey)/(number of women age 15-49 interviewed in the survey)

Since my outcome is child weight:

(1) Could I re-normalize the weigths using this conversion factor?

V005*=V005×(total children age 0-5 in the country at the time of the survey)/(number of children age 0-5 interviewed in the survey)

(2) is there other way to re-normalize the weight that you could suggest to me?


Thank you so much
Re: weighting child data [message #13865 is a reply to message #13845] Tue, 16 January 2018 08:03 Go to previous messageGo to next message
Oquendo is currently offline  Oquendo
Messages: 1
Registered: January 2018
Member
We're also in the middle of a project in which we need to account for weight renormalization. No one on our team is sure how to do this. If anyone knows the best way to do this, we would appreciate it a lot. Thank you.
Re: weighting child data [message #13869 is a reply to message #13845] Tue, 16 January 2018 12:31 Go to previous messageGo to next message
Liz-DHS
Messages: 1351
Registered: February 2013
Senior Member
A response from senior sampler, Dr. Ruilin Ren:
Quote:

For Q#1: The answer is no. The "re-normalize" (rather d-normalize in our words) is to reverse the normalization procedure, so it has to use the women population size and sample size. The children's population size and sample size were not used in the weight normalization.

For Q#2: The answer is no. As stated in the question above, "re-normalization" is to remove the normalization factor from the normalized weight, there is no other way. But if you pool different survey data from the same country, you can "re-normalize" the weight using number of households to approximate, this assumes that the average number of women 15-49 per household is constant across surveys.

V005*=V005×(total number of residential households in the country at the time of the survey)/(number of households interviewed in the survey)

Re: weighting child data [message #15041 is a reply to message #13869] Mon, 28 May 2018 00:27 Go to previous messageGo to next message
sadya2018@gmail.com
Messages: 97
Registered: April 2018
Location: Ethiopia, in Africa
Senior Member
Thank you all!!

Hassen Ali Hamza (BSc in Public Health,Master of Public Health Candidate)
Re: weighting child data [message #15559 is a reply to message #13869] Sat, 11 August 2018 18:49 Go to previous messageGo to next message
slolib86 is currently offline  slolib86
Messages: 3
Registered: December 2017
Location: Peru
Member
Dear all, I have a question about calculating a mean after pooled two o more surveys.

I read a post before and it said: "You should not do analyses that combine the surveys in the sense of calculating a single mean for two surveys, because such a number would not refer to a well-defined population and is not interpretable".

Could you please share a more detailed answer or comment about why does this analyses would not refer to a well defined population and adictionally, this kind of analyses are not interpretable?

thank you so much for your response

https://userforum.dhsprogram.com/index.php?t=msg&goto=10 054&&srch=mean+for+two+survey#msg_10054
Re: weighting child data [message #15621 is a reply to message #15559] Fri, 24 August 2018 11:18 Go to previous message
Liz-DHS
Messages: 1351
Registered: February 2013
Senior Member
A response from Dr. Tom Pullum:
Quote:

Suppose some variable you are interested in had only been collected in, say, a survey with 1000 cases in Peru in 1990 and a survey with 5000 cases in Kenya in 2010. Would you combine them into a single file with 6000 cases and calculate the mean of the variable? Would that mean be interpretable?


Previous Topic: Sex and survival of preceding child
Next Topic: Infat and Young child feeding
Goto Forum:
  


Current Time: Tue Oct 23 10:37:20 Eastern Daylight Time 2018