The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Topics » General » Missing data
Missing data [message #168] Wed, 20 March 2013 15:13 Go to next message
vcostales is currently offline  vcostales
Messages: 1
Registered: March 2013
Member
Hello,
I am looking at the Individual Recode and Household Recode files for the Philippines, Pakistan and Indonesia. The variables for age and education are all missing. Am I looking at the wrong data sets? We also checked the household member recode and that was empty as well. Has someone encountered this problem? Thanks in advance for your help!

Thanks,
Victoria
Re: Missing data [message #293 is a reply to message #168] Wed, 10 April 2013 11:07 Go to previous messageGo to next message
Bridgette-DHS is currently offline  Bridgette-DHS
Messages: 3017
Registered: February 2013
Senior Member
You need to first check first to see whether the questions were asked in the household and individual questionnaires. Sometimes the questions are different from the standard, and they are renamed with a prefix "SH" followed by the question number (if asked in the household questionnaire), by the prefix "S" followed by the question number (if in the woman's questionnaire), and "SM" followed by the question number (if in the man's questionnaire).

You could also search for the string: "age" or "education" in the .map file, which is the data file layout or codebook. This file can be opened with any text editor.
Re: Missing data [message #3159 is a reply to message #293] Sat, 25 October 2014 11:03 Go to previous messageGo to next message
Valko is currently offline  Valko
Messages: 12
Registered: October 2014
Member
Hello.

What is a maximum allowable share of missing values in SPSS for including them into analysis? Why i am asking because in DHS-6 Kyrgyzstan, Males questionnaire, MV504 `Currently residing with a partner/wife` the missing values cover 39.5 per cent. At the same time, MV384B `On TV saw about Family Planning in the last few months`, the missing values constitute 0.1 per cent. Can i use the data from MV504 in the research?

thank you.
Valeriya
Re: Missing data [message #3165 is a reply to message #168] Tue, 28 October 2014 10:25 Go to previous messageGo to next message
Trevor-DHS is currently offline  Trevor-DHS
Messages: 787
Registered: January 2013
Senior Member
I think you need to review the questionnaire closely. Variable MV504 is only asked if the respondent is currently married or living together with someone as if married. You need to select the correct denominator before looking further at the data. Thus for MV504 you would use this only if MV501 is 1 or 2. If you tabulate MV504 with this condition you will see that there are 0.68% of values missing (code 9).
Re: Missing data [message #3170 is a reply to message #3165] Wed, 29 October 2014 11:41 Go to previous message
Valko is currently offline  Valko
Messages: 12
Registered: October 2014
Member
Dear Trevor-DHS,

i am very thankful for your clarifications.

with kind regards,
Valeriya
Previous Topic: Recoded data
Next Topic: Education- Stata
Goto Forum:
  


Current Time: Thu Mar 28 19:37:33 Coordinated Universal Time 2024