Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: st: DFBETA with survey weights in regression
From
Nick Cox <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
RE: st: DFBETA with survey weights in regression
Date
Thu, 17 Mar 2011 15:10:39 +0000
The answer was, I think, in effect: Yes, and please read the talk. However, a quick search implies that the code is not yet public, so you might need to contact the author.
Nick
[email protected]
gemini mtei
Not sure i have got you correct. But analyzing influential observation using DFBETA on plain data might not be the same as when incorporating survey weights in regression. Using survey weights could make some observations influential although not captured when using DFBETA on level data. I thought there might be a way of analyzing infuential observations in stata if survey weights are used.
--- On Thu, 17/3/11, Stas Kolenikov <[email protected]> wrote:
> From: Stas Kolenikov <[email protected]>
> DFBETAs are supposed to work with
> plain data. Rick Valliant talked
> about regression diagnostics at Stata Conference 2009:
> http://www.stata.com/meeting/dcconf09/dc09_valliant.pdf.
>
> On Thu, Mar 17, 2011 at 7:53 AM, gemini mtei <[email protected]>
> wrote:
> > I am running a linear model incorporating survey
> weight and clustering effect in the model (survey design).
> However i am not able to use the normal DFBETA command in
> STATA to analyze influential observation. Does any one knows
> if there is a way of analyzing influential observations when
> survey weights are incorporated in regression?
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/