Following is a response from DHS Senior Sampling Specialist, Mahmoud Elkasabi:
Yes, what you found is correct. You need to create a stratification variable based on the governorates by urban/rural. Since this survey is a country specific survey and does not follow the DHS traditions in naming the survey variables, different names are used for governorates (hgovern) and urban/rural (htype). Below is a Stata code that can be used to create the stratification variable:
egen strata=group(hgovern htype)
[Updated on: Fri, 25 September 2020 09:51]
Report message to a moderator