|
Re: how to reproduce Ghana DHS 2014 published sampling errors and deft values [message #21708 is a reply to message #21623] |
Fri, 11 December 2020 08:26 ![Go to previous message Go to previous message](/theme/default/images/up.png) |
Bridgette-DHS
Messages: 3151 Registered: February 2013
|
Senior Member |
|
|
Following is a response from DHS Lead Statistician, Ruilin Ren:
ICF developed a SAS package for sampling error calculations which produces the Appendix B in the DHS final report. This package uses the SAS PROC SURVEYMMEANS for variance calculation, but this SAS PROC does not calculate the Design Effect (DEFT). The DEFT in appendix B is calculated using an ICF developed module in the package. The DEFT is calculated as the square root of the ratio of variance calculated by PROC SURVEYMEANS, divided by the estimated variance of the same indictor, if the sample had been selected by simple random sampling without replacement. This second component is easy to calculate because it is basically to estimate the population variance based on the survey data.
Hope this helps
|
|
|