Re: total population factors for all women [message #12362 is a reply to message #12357] |
Fri, 05 May 2017 08:51   |
Bridgette-DHS
Messages: 3230 Registered: February 2013
|
Senior Member |
|
|
Following is a response from Senior DHS Stata Specialist, Tom Pullum:
You are apparently using the IR files from these surveys. It could be easier to use the PR files. For example, if you go to the PR file for the Egypt 1992-93 survey, EGPR21FL.dta, you have sex (hv104), age in single years (hv105), level of schooling (hv106), and single years of schooling (hv108). This file includes all women, men, and children in the household sample. You can use the weight variable (hv005) to get the distributions you want. The restriction to ever-married women only affects the IR file. You could use that file, with weights v005*awfacte (awfacte, not awfactu), but that would not be as accurate or as easy as using the PR file.
|
|
|