The DHS Program User Forum: India » Weighting variables in DHS India data (1992 and 1998)

Home » Countries » India » Weighting variables in DHS India data (1992 and 1998)

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

Re: Weighting variables in DHS India data (1992 and 1998) [message #7044 is a reply to message #7042]

Sun, 16 August 2015 17:11

Reduced-For(u)m
Messages: 292
Registered: March 2013

Senior Member

The problem with doing the weighting manually (instead of via the "svy" prefix) is not in the weighting, but in the stratification and clustering. That is, your command will weight the observations just fine, but won't account for other aspects of the survey design.

The clustering at PSU could be done manually ", cluster(psu)", but I am not sure there is a good, easy way to manually account for the stratification (in the sampling procedure).

Your version (just the manually used weights) will produce standard errors that are too small (your p-values will be too small, and you'll reject a true null hypothesis too often). Adding in clustering at the PSU level will produce almost right standard errors (or p-values, or CIs) but they may be a little too big since they don't account for the stratification. Using the "svy" prefix guarantees not just that you get good population level estimates of means/differences (weighting) but also more appropriate statistical inference properties (rejection rates, CI coverage rates, however you want to think of that).

Report message to a moderator

[Message index]

		Weighting variables in DHS India data (1992 and 1998) By: user_rm on Thu, 06 August 2015 13:20
		Re: Weighting variables in DHS India data (1992 and 1998) By: Bridgette-DHS on Fri, 07 August 2015 09:33
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Fri, 07 August 2015 11:00
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Wed, 12 August 2015 19:01
		Re: Weighting variables in DHS India data (1992 and 1998) By: Bridgette-DHS on Thu, 13 August 2015 11:26
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Fri, 14 August 2015 14:07
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Sun, 16 August 2015 12:14
		Re: Weighting variables in DHS India data (1992 and 1998) By: Reduced-For(u)m on Sun, 16 August 2015 17:11
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Sun, 16 August 2015 17:17
		Re: Weighting variables in DHS India data (1992 and 1998) By: Reduced-For(u)m on Sun, 16 August 2015 20:59
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Tue, 18 August 2015 13:06
		Re: Weighting variables in DHS India data (1992 and 1998) By: Bridgette-DHS on Wed, 26 August 2015 07:37
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Tue, 01 September 2015 08:34
		Re: Weighting variables in DHS India data (1992 and 1998) By: Bridgette-DHS on Tue, 01 September 2015 12:41
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Tue, 08 September 2015 09:07
		Re: Weighting variables in DHS India data (1992 and 1998) By: Bridgette-DHS on Thu, 10 September 2015 06:09
		Re: Weighting variables in DHS India data (1992 and 1998) By: user_rm on Fri, 11 September 2015 06:12
		Re: Weighting variables in DHS India data (1992 and 1998) By: Bridgette-DHS on Fri, 18 September 2015 14:17

Previous Topic:	Caste unique identifier
Next Topic:	Religion in NFHS-1

Goto Forum:

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Wed Nov 27 22:17:33 Coordinated Universal Time 2024