Home » Data » Dataset use (other programs) » Uttar Pradesh districtwise Neonatal, infant, postnatal and under five Mortality data (Stata for required processing Uttar Pradesh districtwise Neonatal, infant, postnatal and under five Mortality data From NFHS 5 Datasets)
Uttar Pradesh districtwise Neonatal, infant, postnatal and under five Mortality data [message #26992] |
Wed, 07 June 2023 03:47 |
Shruti Singh
Messages: 3 Registered: June 2023
|
Member |
|
|
Hello Everyone,
I am working with NFHS 5 Data using Stata version 14.2. I am in need of Uttar Pradesh district wise Neonatal, infant, postnatal and under five Mortality data. I have downloaded all the NFHS 5 datasets but I am unable to process required data from that. Please share Stata codes for processing Uttar Pradesh district wise Neonatal, infant, postnatal and under five Mortality data which also include GPS Coordinates of that place. Also guide me how to convert these datasets in tabular format on excel sheet. These data are very critical for my dissertation. Kindly share and help ASAP.
Thanks
Shruti Singh
M.Sc. Environmental Sciences
Banaras Hindu University
|
|
|
|
|
Re: Uttar Pradesh districtwise Neonatal, infant, postnatal and under five Mortality data [message #26999 is a reply to message #26996] |
Thu, 08 June 2023 07:43 |
Bridgette-DHS
Messages: 3208 Registered: February 2013
|
Senior Member |
|
|
Following is a response from Senior DHS staff member, Tom Pullum:
Your request goes far beyond the scope of the forum. Also what you propose to do would not be useful, because of the statistical uncertainty of district-level estimates.
However, I have prepared something that may be useful. I wrote a Stata program to calculate, within the districts of Uttar Pradesh, the proportion of children born in the past five years who had died by the date of the survey, along with 95% confidence intervals adjusted for the survey design. This program could be of interest to other users so I will paste it below (as a text file). Since you wanted an Excel file, I am attaching the Excel file that is produced by this program.
You will see that the confidence intervals are wide. The confidence intervals for the standard rates would be much wider. The proportion calculated here is probably the best you can do to identify variation in child survival across districts.
* Program to calculate the proportion of children in the NFHS5 KR file
* who survived to the date of the survey, in districts in Uttar Pradesh
* Specify a workspace
cd e:\DHS\DHS_data\scratch
* Open the KR file; children born in the past 5 years
use "C:\Users\26216\ICF\Analysis - Shared Resources\Data\DHSdata\IAKR7EFL.DTA", clear
describe v024
* The label for v024 is V024; list it
label list V024
* Uttar Pradesh is v024=9
keep if v024==9
* How many districts are in Uttar Pradesh?
codebook sdist
* 75 districts
svyset v001 [pweight=v005], strata(v023) singleunit(centered)
svy: proportion b5, over(sdist)
* the lines with the output "0" give the proportion of children who died, with a confidence interval
* Save the results and copy into Excel
matrix S=r(table)
matrix T=S'
* construct a file with the district names and n's, weighted and unweighted
gen unwtdn=1
gen wtdn=sweight/1000000
collapse (sum) *wtdn,by(sdist)
rename sdist district
label values district SDIST
label variable unwtdn "N (unweighted)"
label variable wtdn "N (weighted)"
gen line=_n
sort line
save stub.dta, replace
clear
svmat T
matrix list T
rename T1 b
rename T2 se
rename T3 t
rename T4 pvalue
rename T5 ll
rename T6 ul
rename T7 df
rename T8 crit
rename T9 eform
gen line=_n
keep if line<=75
sort line
merge line using stub.dta
tab _merge
rename b P
rename ll L
rename ul U
label variable P "Proportion dead"
label variable L "Low end, 95% c.i."
label variable U "Upper end, 95% c.i."
keep district P L U *wtdn
order district P L U *wtdn
list, table clean
export excel using child_survival_by_district.xlsx, replace firstrow(var)
|
|
|
Re: Uttar Pradesh districtwise Neonatal, infant, postnatal and under five Mortality data [message #27011 is a reply to message #26999] |
Sat, 10 June 2023 04:18 |
Shruti Singh
Messages: 3 Registered: June 2023
|
Member |
|
|
Dear Sir,
I am very much grateful for your help . It is great support and clarity given by you to my work. But I am in dilemma as I have to correlate Uttar Pradesh district wise Neonatal, infant, postnatal and under five Mortality data with air pollution. For that I need little more accurate Stata coding and excel sheet conversion for following mentioned terms-
1. Number of live births for each year survey, including monthly/daily/yearly record of
each year.
2. Number of neonatal deaths for each year survey, including monthly/daily/yearly
record of each year
3. Detailed information on neonatal deaths, including but not limited to:
a. Causes of neonatal mortality, specifically deaths related to air pollution (if
available). b. Geographical distribution of neonatal deaths.
c. Relevant demographic information, such as age, gender, and socioeconomic status
of the infants.
d. Any available information on the duration and intensity of air pollution exposures
preceding neonatal deaths.
Date of interview, year of survey, no of observation district wise Neonatal, infant, postnatal and under five Mortality data
Regards
|
|
|
Re: Uttar Pradesh districtwise Neonatal, infant, postnatal and under five Mortality data [message #27017 is a reply to message #27011] |
Mon, 12 June 2023 08:35 |
Bridgette-DHS
Messages: 3208 Registered: February 2013
|
Senior Member |
|
|
Following is a response from Senior DHS staff member, Tom Pullum:
In the KR and BR files, b7 gives age at death in completed months for children who died. Thus b7=0 for neonatal deaths, b7 is 1 to 11 for postneonatal deaths, 0 to 11 for infant deaths. You can construct child-level measures of mortality at different ages and use logit regression to relate mortality to air pollution indicators within the household. You could include a 'random effect' for district, but it would not be helpful to do separate analyses within each district. There are just too many districts, even within just one state.
The type of analysis you propose is complex. Excel spreadsheets would be cumbersome and inefficient. You will have to simplify the analysis so that you can do it yourself. DHS staff cannot help further.
|
|
|
Goto Forum:
Current Time: Wed Dec 11 15:18:16 Coordinated Universal Time 2024
|