The DHS Program User Forum
Discussions regarding The DHS Program data and results
Today's Messages (off)  | Unanswered Messages (on)

Forum: Biomarkers
 Topic: Merging CR and PR file
Merging CR and PR file [message #19322] Fri, 29 May 2020 23:16
nagar002 is currently offline  nagar002
Messages: 7
Registered: April 2018
Hi DHS users,

I am looking for some help about merging the CR file with the PR file (need to bring husband's anemia from the PR file to the CR file). I have written the following code and I'll appreciate if someone can provide feedback about the correct way to do this. I couldn't find any post about the link of CR and PR file.

And are the duplicates in line three of the code below due to one man married to more than one female?

use "IACR74FL.DTA", clear
sort v001 v002 v034
quietly by v001 v002 v034: gen dup = cond(_N==1,0,_n) //why are there duplicates here?
drop if dup>0
tempfile cr
save `cr', replace

use "IAPR74FL.DTA", clear
ren hv001 v001
ren hv002 v002
clonevar v034=hvidx
sort v001 v002 v034
keep v001 v002 v034 hb57
merge 1:1 v001 v002 v034 using `cr'
keep if _m==3

<This example is for India. I have more countries in my sample, but I believe the basic idea can be used as it is for other surveys.>

In essence, my question is can we use v034 (the variable that identifies the husband in CR file) to bring information from the PR file about the husband?

Thanks you for any help.

[Updated on: Fri, 29 May 2020 23:18]

Report message to a moderator

Forum: Child Health
 Topic: Sampling Weigths for children under 5
Sampling Weigths for children under 5 [message #19318] Fri, 29 May 2020 11:16
rafaaqp1990 is currently offline  rafaaqp1990
Messages: 1
Registered: May 2020
Dear all,
I am new to survey data and I am having trouble trying to find my error in my R-Code. I chose Philippines 2017 and I am trying to calculate the percentage of vitamin A supplementation for this country for children under 5.

This is my R-Code

phi17 <- read.dta("PHKR71FL.DTA")
# Using labels as column names
var.labels <- attr(phi17, "var.labels")
names(phi17) <- var.labels

For speficying the model I use the following code:

# Simplifying column names
phi17$weight <- as.numeric(phi17$`women's individual sample weight (6 decimals)`/1000000)
phi17$psu <- phi17$`primary sampling unit`
phi17$strata <- phi17$`stratification used in sample design`
phi17$vi_a = phi17$`vitamin a in last 6 months`

phi_17_design <- svydesign(~ psu,
strata = ~strata,
weights = ~ weight,
data = phi_17)

So, I used the weights for the women but when I calculate the percentage of children who received a vitamin A supplement in the last 6 months in Philippines 2017, i get the following results:
svymean(~ vi_a, phi_17_design, na.rm = TRUE) --> yes: 69.47%

HOWEVER, when I read the final report, the result should actually be 76%.

Does anyone recognize the mistake? Did I specified the weigths correctly??

Thank you in advance!

Best regards


Forum: Dataset use in Stata
 Topic: Afghan 2015 DHS
Afghan 2015 DHS [message #19316] Fri, 29 May 2020 00:19
rbsi17 is currently offline  rbsi17
Messages: 1
Registered: May 2020
I'm currently doing research using the 2015 Afghan DHS and I have a couple questions surrounding fever prevalence and how it was recorded in the survey. Firstly, how did families determine if their child had a fever? Was it through use of thermometers, feeling their child's head, knowledge of their child having a certain illness? Also, does anyone who conducted the survey know about recent outbreaks of the flu or if the surveys were conducted during a flu season that may have peaked the prevalence of fever among populations? Lastly, there was a high number of missing data pertaining to fever prevalence among populations (75.4%) How do you recommend me going about using this data knowing that there is such a high volume of missing data?
Forum: Wealth Index
 Topic: Lesotho Urban/Rural Ns
Lesotho Urban/Rural Ns [message #19315] Thu, 28 May 2020 18:59
hannaheow is currently offline  hannaheow
Messages: 1
Registered: May 2020
I think there is a typo in 'Lesotho DHS 2014.xlsx' found here: truction.cfm.
The Analysis N (9402) used in the 'Common' tab is the same as the Analysis N used in the 'Urban' tab. And the Analysis N (2798) used in the 'Rural' tab is the same as the value I found for urban (variable HV025 == 1). Urban+Rural = Common, correct? But this is not the case in the xlsx document.

Thanks for looking into this!
Forum: India
 Topic: women india
women india [message #19312] Thu, 28 May 2020 11:55
filippo is currently offline  filippo
Messages: 2
Registered: May 2020
Hi everyone I'm worrking with IAIR74FL so DHS 2015-2016. In the stata file there is no the variable relating to the below poverty line card, I need that information. Is there any way to procede?
thank you
Forum: Ethiopia
 Topic: Changing prevalence and factors associated with Female Genital Mutilation in Ethiopia using EDHS
Changing prevalence and factors associated with Female Genital Mutilation in Ethiopia using EDHS [message #19310] Wed, 27 May 2020 15:25 is currently offline
Messages: 1
Registered: May 2020
Dear sir/madam

I am using the 2000, 2005 and 2016 Ethiopian DHS datasets (SPSS software package) for my registered project titled 'Changing prevalence and factors associated with Female Genital Mutilation in Ethiopia: data from the 2000, 2005 and 2016 National Demographic Health Surveys'. The three datasets from EDHS were weighted using standard methodology before the actual analysis; I created the weight variable 'WGT=V005/1000000' and then, I applied the weight (WGT) before running any tabulation. After applying sampling weight, I ran the frequency analysis for Female Genital Mutilation (FGM) and I found the same proportion with the final EDHS in 2000 (79.9%) and 2005 (74.3%) available on the DHS website. Although I used the same method to apply sample weights for each datasets, My finding for the proportion of FGM in the 2016 EDHS (70.4%) was different from that reported from the official final EDHS report which was 65%. I am having difficulties with the 2016 EDHS dataset with respect to matching the proportion of FGM (70.4%) with the final official EDHS report which is 65%. I would very much appreciate any help you can give us here

Current Time: Mon Jun 1 02:13:15 Eastern Daylight Time 2020