Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: conditional SE of y|X in glm


From   Marco Ventura <mventura@istat.it>
To   statalist@hsphsun2.harvard.edu
Subject   st: conditional SE of y|X in glm
Date   Tue, 24 Apr 2012 10:31:19 +0200

Dear Stata users,
I'm having the following problem:
from a GLM estimate I want to retrieve the conditional standard error of y given the covariates. If I do

gen sigma=sqrt(e(dispers))

do I always get the right thing independently of any family and link?
Should I correct it by sqrt(e(dispers)* (_N-1)/_N)?
And do you think I should instead use the Pearson residuals such as

gen sigma=sqrt(e(dispers_p))

Thank you very much of your courtesy.
Kind Regards,
Marco

--
*****************************************
Marco Ventura
Researcher at ISTAT
Italian National Institute of Statistics
Econometric Studies and Economic Forecasting Division
P.zza Dell'Indipendenza 4, 00185 Rome, Italy
tel: (+39)064673 3665
http://www.isae.it/Ricercatori_e_Tecnologi/Ventura_ital_con_CV_inglese.pdf
fax: (+39)06233232 419


*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index