The DHS Program User Forum - RDF feed
https://userforum.dhsprogram.com/index.php
Re: Using weights in regression analysis
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=18672&th=2172#msg_18672
]]>kindu2020-01-25T17:38:12-00:00Weighting for multi-country data
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=17978&th=8305#msg_17978
I am planning to analyze multicountry data (sub-Saharan countries) on household drinking water handling practices. I can weight the data at the household level using
gen WGT= v005/1000000
svyset [pw=WGT], psu(v021) strata(v022)
But, I want to know whether it is possible to weight data both at the community(within the country) and at the country level.
Or How can I creat weighted varibale for country (wvar3) and community (wvar2) to run multilevel modeling as:
melogit y x [pw=WGT] ||country:, pw(wvar3) || community:, pw(wvar2)?
Abraham
]]>Abraham2019-08-07T12:53:18-00:00Re: Webinar Recording and Script now available
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=14767&th=3238#msg_14767
Hassen2018-05-04T11:12:50-00:00You tube videos on sampling & weights (parts 1-4) - slides?
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=13239&th=6410#msg_13239
I watched the DHS sampling and weighting videos and they were very helpful. I was wondering if there is a way to download the slides (looks like they were ppt) as they would be very useful for us. The transcripts were very helpful which I turned on, and if we can have the slides that could be a handy reference.
Thanks for considering this.
Sincerely,
newtoDHS2017]]>newtoDHS20172017-10-08T17:04:05-00:00Re: Reproducing tables: Health Insurance coverage in the Ghana 2008 DHS
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=11616&th=5808#msg_11616
Could you please repost this question in the Data/Weighting section of the Forum? This thread was about about a webinar that took place in June 2015, so it is not particularly active.
Thanks,
Sarah-DHS]]>Sarah-DHS2017-01-17T13:19:07-00:00Reproducing tables: Health Insurance coverage in the Ghana 2008 DHS
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=11607&th=5808#msg_11607
I am trying to generate values similar to Table 3.8.1 Health insurance coverage: Women but I am not sure of the appropriate sampling weights I should use to achieve a table as below.
Kindly advice.]]>kjacob2017-01-16T06:17:15-00:00Re: Webinar Presentation Available Here!
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=10644&th=3230#msg_10644
Due to audio recording issues we were unable to post a recording of the webinar. However, the PowerPoint presentation is available at the top of this thread.
Thank you,
Sarah-DHS]]>Sarah-DHS2016-08-24T12:15:13-00:00Re: Webinar Presentation Available Here!
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=10643&th=3230#msg_10643
Was a recording of the webinar ever posted, and if so, where? I am unable to locate it.
Thank you!]]>tarheel2016-08-24T03:48:46-00:00Re: Webinar Presentation Available Here!
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=8824&th=3230#msg_8824
What is the variable for Inter-spousal communication in DHS?
Regards.
ENSI]]>Abisiku2015-12-24T12:30:51-00:00Re: pweight vs iweight
https://userforum.dhsprogram.com/index.phpindex.php?t=rview&goto=7059&th=3225#msg_7059
The meaningful difference between iweights and pweights, as I understand it, is the formula used to calculate SEs, in that pweights produce robust SEs. So while iweights and pweights produce the same means, proportions, and frequencies, the SEs, CIs, and calculations of statistical significance will be different when using iweights vs. pweights. So for any calculations involving uncertainty estimation, pweights are indeed the appropriate option.