| Children from same household [message #14225] |
Tue, 06 March 2018 22:46  |
phyumar
Messages: 18
Registered: February 2018
Location: Singapore
|
Member |
|
|
Hello Sir,
I am looking at Bangladesh DHS data (BDKR72FL) file for estimating factors influencing common childhood illnesses.
It would be great that if you could enlighten me the following questions:
- When I tried to compare my weighted results with Bangladesh DHS report page 142, Table 10.4 Diarrhoea and background characteristics particularly by sex.
I got the same estimated proportion and absolute number of children who got diahorea in last 2 weeks. However, I got different results in total number of children with or without diarhoea dis-aggregated by sex.
The different is 2 absolute number for male and 4 for female. These are all weighted. Could you kindly let me know why I don't get the same number of children?
Here is my result table,
svy: tab b4 h11,count
(running tabulate on estimation sample)
Number of strata = 21 Number of obs = 7560
Number of PSUs = 600 Population size = 7754.4242
Design df = 579
--------------------------------------------------
sex of | had diarrhea recently
child | no yes, las don't kn Total
----------+---------------------------------------
male | 3803 232.2 13.37 4049
female | 3490 208.2 7.439 3706
|
Total | 7293 440.4 20.81 7754
--------------------------------------------------
Key: weighted counts
The report described 4051 male and 3710 female.
- I also want to know the children from the same household. Which variable represent this information? I see that the variable "caseid" has the same numbers and hidx has different numbers then can we assume that these children are from same household!
- If I want to know birth order of the child, can I use the variable "bord"?
Thanks you so much in advance for clarifying all those queries.
Best regards,
Phyumar
|
|
|
|
| Re: Children from same household [message #14297 is a reply to message #14225] |
Tue, 20 March 2018 08:41  |
Bridgette-DHS
Messages: 3208
Registered: February 2013
|
Senior Member |
|
|
Following is a response from Senior DHS Stata Specialist, Tom Pullum:
Sorry for the delay with this reply. First, I am looking into the extra six cases that seem to be in table 10.4. Will let you know when I know more about that. Second, caseid is the id code for the mother. It is a string that includes v001, v002 v003 from the IR file, which are the same as or hv001, hv002, hvidx in the PR file. Children with the same value of caseid will have the same mother, and be in the same household, but there can be more than one eligible woman, or mother, in the same household. Children in the same household will have the same values of v001 and v002 (or hv001 and hv002). The line number in the household file (hvidx) of the child is given in the KR and BR files as b16. Third, the birth order of the children of a specific mother is indeed given by bord, which is numbered from the first birth to the most recent birth. By contrast, bidx is numbered backwards, from the most recent birth to the earliest birth.
|
|
|
|
|
|
| Re: Children from same household [message #14319 is a reply to message #14308] |
Thu, 22 March 2018 11:55 |
Bridgette-DHS
Messages: 3208
Registered: February 2013
|
Senior Member |
|
|
Following is another response from Senior DHS Stata Specialist, Tom Pullum:
If a child has died, indicated by b5=0, then b16 will be NA and coded ".". If a child has survived but is not living in the same household as the mother, the line number is "0".
|
|
|
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
