Re: Road traffic accident [message #27863 is a reply to message #27842] |
Fri, 13 October 2023 13:35 |
Janet-DHS
Messages: 893 Registered: April 2022
|
Senior Member |
|
|
Following is a response from DHS staff member, Tom Pullum:
I can't tell how far you were able to get with the construction of a data file. Below I will paste Stata lines to do this and then to merge with the PR file.
* Nepal 2022
* Analyze the accidents and injuries data in the HR file
use "...NPHR82FL.DTA", clear
keep hv0* hai*_*
drop *idx
describe hai*_1
* There are many hai variables; here is a way to itemize them for the reshape long command
local lnum 1 2 3 4 5 6 7 8 10 11 12 13o 13p
scalar ss=" "
foreach ll of local lnum {
scalar ss=ss+"hai`ll'_ "
}
local llet a b c d e f g h i j k l m n x z
scalar s9=" "
scalar s13=" "
foreach ll of local llet {
scalar s9=s9+"hai9`ll'_ "
scalar s13=s13+"hai13`ll'_ "
}
scalar list ss s9 s13
local ls=ss
local l9=s9
local l13=s13
reshape long `ls' `l9' `l13', i(hv001 hv002) j(event)
rename *_ *
tab hai1,m
drop if hai1==.
* This does not keep the variable labels
label variable hai1 "accident type"
label variable hai8 "death related to the accident"
tab hai1 hai8,m
label variable hai10 "line number"
* specify a workspace
cd e:\DHS\DHS_data\scratch
* Merge the accidents with the PR file
gen cluster=hv001
gen hh=hv002
gen line=hai10
sort cluster hh line
save temp.dta, replace
use "...NPPR82FL.DTA", clear
gen cluster=hv001
gen hh=hv002
gen line=hvidx
sort cluster hh line
merge cluster hh line using temp.dta
tab _merge
I have not seen these variables included in any other DHS survey and am not sure of the interpretation. It appears that there are only 7 (unweighted) deaths from traffic accidents during the reference period for the questions.
In the merge with the PR file, note that hai10 is NA (a dot) for people who died or are no longer in the household, and it is possible for more than one accident/injury to happen to a person. Let us know if you have other questions.
|
|
|