| Re: NFHS 3 PSU scrambling question [message #30470 is a reply to message #30436] |
Wed, 04 December 2024 14:43  |
Janet-DHS
Messages: 911
Registered: April 2022
|
Senior Member |
|
|
Following is a response from DHS staff member, Tom Pullum:
Households are NEVER switched from one PSU to another.
In all DHS surveys, the PSU codes are scrambled--in the sense that they are changed from what they were in the original sampling frame, in order to protect the confidentiality of the selected households and respondents. That has nothing to do with whether the survey included HIV testing.
The GPS coordinates for a PSU are always displaced randomly within a circle around the original GPS coordinates, but staying within the same district. The displacement procedure is described in our basic documentation. The displaced coordinates are given in geographic data files, and DHS does not retain the original coordinates.
The NFHS-3 (the India 2005-06 DHS survey) does not have geographic data or geographic covariates files. Other surveys from about the same years do have such files, but I doubt that the absence of geographic files has anything to do with the HIV testing. The NFHS-4 also included HIV testing, and it DOES have geographic files.
The absence of geographic files means that we cannot provide the geographic coordinates (even after displacement) for the PSUs in this survey, and there is no way to link to geographically structured data, at least at the level of the PSU.
|
|
|
|
The DHS Program User Forum
Members
Search
Help
Register
Login
Home
