The DHS Program User Forum: Weighting data » Why I am getting different total observations when using iweight for tabulating a variable

Home » Data » Weighting data » Why I am getting different total observations when using iweight for tabulating a variable

Show: Today's Messages :: Show Polls :: Message Navigator

Re: Why I am getting different total observations when using iweight for tabulating a variable [message #26556 is a reply to message #26552]

Fri, 31 March 2023 12:03

Bridgette-DHS
Messages: 3199
Registered: February 2013

Senior Member

Following is a response from Senior DHS staff member, Tom Pullum:

This is outside the scope of the forum but I'll suggest what MAY be going on. Two conventions regarding the normalization of weights may be in conflict. In the page you attached, the weights are normalized to add to one. That's one convention. However, with pweights (are you using pweights?) Stata automatically normalizes the weights to have a MEAN of 1. So far as I know, with pweights it is actually impossible to over-ride that. Stata does that so the weighted and unweighted totals will match, which is usually desirable from a sampling perspective.

I don't have time to do this, but if I did, I would go over the algebra of the fractional weights to confirm mathematically that the mean should be 0.5 under the first convention and then see what happens when a small set of maybe 10 numbers is analyzed with Stata.

Another option would be to ask one of the authors of the World Bank report. Sorry we can't be more helpful.

Report message to a moderator

[Message index]

		Why I am getting different total observations when using iweight for tabulating a variable By: sujata on Tue, 07 February 2023 12:48
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: Bridgette-DHS on Thu, 09 February 2023 09:11
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: sujata on Thu, 09 February 2023 11:45
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: Bridgette-DHS on Thu, 09 February 2023 13:12
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: sujata on Fri, 10 February 2023 01:31
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: Bridgette-DHS on Fri, 10 February 2023 07:58
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: sujata on Fri, 10 February 2023 10:49
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: sujata on Thu, 30 March 2023 07:02
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: Bridgette-DHS on Thu, 30 March 2023 11:04
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: sujata on Fri, 31 March 2023 07:56
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: Bridgette-DHS on Fri, 31 March 2023 12:03
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: sujata on Sat, 01 April 2023 02:23
		Re: Why I am getting different total observations when using iweight for tabulating a variable By: Bridgette-DHS on Mon, 03 April 2023 08:35

Previous Topic:	Multilevel model with region random effects
Next Topic:	Response rate and weights

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Fri Nov 29 13:51:49 Coordinated Universal Time 2024