The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » General » interviewer identifier
interviewer identifier [message #2177] Sun, 18 May 2014 01:28 Go to next message
Guilhem is currently offline  Guilhem
Messages: 13
Registered: January 2014
Member
Hello,

in a regression analysis, I'd like to control for the identity of the interviewer.
The DHS2 survey, which I am using has a code for interviewer (hv018) which varies from 0 to 99.
This does not seem to uniquely identify the interviewer.
Could you tell me with which other variable I should combine hv018 in order to get to a unique interviewer ID ?

Many thanks,

Guilhem
Re: interviewer identifier [message #2180 is a reply to message #2177] Tue, 20 May 2014 15:14 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
If you are looking at a frequency of HV018, the codes indicate the codes which were assigned to the interviewers. Those codes for all intents and purposes uniquely identify the interviewers. HV018 for the household questionnaire and V028 for the individual questionnaire. In most cases these should be the same code as we expect an interviewer to interview the houshold and all the individuals within that household.
If you still have questions, please feel free to post again.
Re: interviewer identifier [message #2181 is a reply to message #2180] Tue, 20 May 2014 15:24 Go to previous messageGo to next message
Guilhem is currently offline  Guilhem
Messages: 13
Registered: January 2014
Member
Am I right in understanding that using only the variable hv018 identifies a single interviewer.
I.e, that there were exactly 100 interviewers for DHS in whole India, with some interviewing as little as 2 households and others more than 3000 ?
That sounds surprising to me (but I of course could be wrong), which is why I believe hv018 needs to be combined with other identifiers (for exemple state and/or district) to attribute a unique ID to a unique interviewer.
If the latter is correct, could you tell with which other variables I should combine hv018 in order to create a variable that would take a unique value for a unique interviewer ?

Many thanks
Re: interviewer identifier [message #2185 is a reply to message #2181] Wed, 21 May 2014 09:37 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
Let me look into this further and get clarification. I will check with one of our experts and get back to you. Can you please let me know exactly which survey and year your are asking about?
thank you!
Re: interviewer identifier [message #2186 is a reply to message #2177] Wed, 21 May 2014 09:39 Go to previous messageGo to next message
Guilhem is currently offline  Guilhem
Messages: 13
Registered: January 2014
Member
I am using the second round of the Indian DHS (household module).

Many thanks for your help.
Re: interviewer identifier [message #2190 is a reply to message #2186] Wed, 21 May 2014 10:13 Go to previous messageGo to next message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
The India 1998-99 data?
Thanks!
Re: interviewer identifier [message #2191 is a reply to message #2190] Wed, 21 May 2014 10:16 Go to previous messageGo to next message
Guilhem is currently offline  Guilhem
Messages: 13
Registered: January 2014
Member
Yes, the 1998-9 Indian round.
Re: interviewer identifier [message #2192 is a reply to message #2191] Wed, 21 May 2014 10:36 Go to previous message
Liz-DHS
Messages: 1516
Registered: February 2013
Senior Member
Dear User,
After reviewing the frequencies and speaking with one on of our experts, the variable you also need to be looking at is the region (State) variable which is HV024. This together with HV018 will give you a unique interviewer number.
Thank you!
Previous Topic: sex disaggregation of asset ownership
Next Topic: NFHS report 2005 - 06
Goto Forum:
  


Current Time: Thu Mar 28 19:22:31 Coordinated Universal Time 2024