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]
st: conditional SE of y|X in glm
From
Marco Ventura <[email protected]>
To
[email protected]
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/