| Response code as "In-consistence" be valuable to include in analysis ? [message #18019] |
Sun, 18 August 2019 05:11  |
drseinhlaing
Messages: 7
Registered: August 2019
|
Member |
|
|
Dear DHS specialist
I am analyzing FP unmet need and it predictors in Myanmar DHS 2015-16. In Myanmar DHS data, for example : v531 : Age at first Sex (Imputed) , there is responses coded as "In-consistence". I would like to ask , what should be the suitable practice of managing this category of responses - "In-consistence" while analyzing association between v531 ( predictor variable) and FP-Unmet need ( out come variable) ?
Similarly, another example of V729, Husband / partner Education attainment , there is responses coded as "Don't Know". what should be the suitable practice of managing this category of responses - "Don't know" while analyzing association between predictor variable and FP-Unmet need ( out come variable) ?
Could I re-coded those responses "In-consistence", "Don't Know" as missing data and treated as missing data? or any other recommended practices to manage those responses recoded as "In-consistence" / "Don't Know".
Thanks for your kind guidance
With regards
Sein Hlaing
[Updated on: Sun, 18 August 2019 05:17] Report message to a moderator |
|
|
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
