Home » Countries » Other countries » Indonesian Special DHS 2002-03 (Problems with Identifier )
Indonesian Special DHS 2002-03 [message #22199] |
Wed, 10 February 2021 19:41 ![Go to next message Go to next message](/theme/default/images/down.png) |
syauqy
Messages: 3 Registered: February 2021 Location: Australia-Indonesia
|
Member |
|
|
Hi,
I am currently using the Indonesian Special DHS 2002-03 Young Adult, and cannot separate the reported observations (1815 women and 2341 men, unmarried, 15-24) and with the rest of the observations from the dataset. I am using STATA, and merged the HOUSEHOLD_IDENTIFICATION.DTA, RESPONDENT_BACKGROUND.DTA and INDIVIDUAL_IDENTIFICATION.DTA to try to make sense of the data.
the qqsex variable enable a sex identifier, with 9997 observations, 5804 male and 4193 female
the variable qqtype, "type of questionnaire", 9997 observations with answer "young adult" (3)
from the variable qresult, "result of individual interview", 8210 completed observations can be separated from the 9997
I checked the qp103 variable that shows "respondent's current age", and found 8210 observations, consistent with the result of qresult
The variable qheligy, "Eligible for young adult survey", resulted 9999 observations answering "yes"
The variable qheligm, "Eligible for male interview", resulted 2846 "yes" (not consistent with report of 2341 men) while qhmen "Eligible Men in Household", resulted 2097 eligible observations (again not consistent with report of 2341 men)
The variable qhwomen, "Eligible Women in Household" resulted 6922 eligible observations.
The variable qhyoung, "Eligible young adult in household" resulted 3840 eligible observations (still not corresponding to 1815 women and 2341 men).
I tried to do crosstabs on these 'eligibility' variable, but still unable to distinguish the observations that were use in the report with the rest of the observations.
I tried to search for answers in the report and the documentation, and also have tried my best to search the forum to no success. Any help would be greatly appreciated!
Thanks,
Syauqy
[Updated on: Wed, 10 February 2021 19:57] Report message to a moderator
|
|
|
Re: Indonesian Special DHS 2002-03 [message #22282 is a reply to message #22199] |
Tue, 23 February 2021 14:18 ![Go to previous message Go to previous message](/theme/default/images/up.png) |
Bridgette-DHS
Messages: 3151 Registered: February 2013
|
Senior Member |
|
|
Following is a response from DHS Research & Data Analysis Director, Tom Pullum:
This survey is about 18 years old and was a Special Survey, as you say, not a standard DHS survey. I took a quick look at the files, and they seem strange. For example, the "individual" file has 9997 cases but 1883 of them have qweight=0. The "respondent" file does not include a weight variable. The age distribution in the "respondent" file is bizarre--1801 cases at age 15 and 205 at age 24. That steep a gradient in the age distribution is impossible. The "household" file has 9999 cases, but 1366 of them have qhweight=0.
If you want to work with these files you will have to do the detective work on your own. You also would do it at your own risk. DHS cannot provide support.
[Updated on: Tue, 23 February 2021 15:32] Report message to a moderator
|
|
|
Goto Forum:
Current Time: Sun Sep 1 02:39:43 Coordinated Universal Time 2024
|