Sigh.
Message: 50
Date: Fri, 26 Apr 2013 10:13:52 +1200
From: Rolf Turner rolf.tur...@xtra.co.nz
To: Terry Therneau thern...@mayo.edu
Cc: r-help@r-project.org, Achim Zeileis achim.zeil...@uibk.ac.at
Subject: Re: [R] Trouble Computing Type III SS in a Cox Regression
Message-ID: 5179aaa0.8060
Seconded
John Kane
Kingston ON Canada
-Original Message-
From: rolf.tur...@xtra.co.nz
Sent: Fri, 26 Apr 2013 10:13:52 +1200
To: thern...@mayo.edu
Subject: Re: [R] Trouble Computing Type III SS in a Cox Regression
On 26/04/13 03:40, Terry Therneau wrote:
(In response
wrote:
From: Terry Therneau thern...@mayo.edu
Subject: Re: Trouble Computing Type III SS in a Cox Regression
To: r-help@r-project.org, Paul Miller pjmiller...@yahoo.com
Received: Wednesday, April 24, 2013, 5:55 PM
I should hope that there is trouble,
since type III is an undefined concept
to determine which predictors are useful and to discard the rest. Is
that likely to be any good?
Thanks,
Paul
--- On Wed, 4/24/13, Terry Therneau thern...@mayo.edu wrote:
From: Terry Therneau thern...@mayo.edu
Subject: Re: Trouble Computing Type III SS in a Cox Regression
To: r-help@r-project.org
You've missed the point of my earlier post, which is that type III is not an answerable
question.
1. There are lots of ways to compare Cox models, LRT is normally considered the most
reliable by serious authors. There is usually not much difference between score, Wald,
and LRT tests
On 26/04/13 03:40, Terry Therneau wrote:
(In response to a question about computing type III sums of squares in a
Cox regression):
SNIP
If you have customers who think that the earth is flat, global warming
is a conspiracy, or that type III has special meaning this is a
re-education
Dear Paul,
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-bounces@r-
project.org] On Behalf Of Paul Miller
Sent: Wednesday, April 24, 2013 1:18 PM
To: r-help@r-project.org
Subject: [R] Trouble Computing Type III SS in a Cox Regression using
drop1 and Anova
I should hope that there is trouble, since type III is an undefined concept for a Cox
model. Since SAS Inc fostered the cult of type III they have recently added it as an
option for phreg, but I am not able to find any hints in the phreg documentation of what
exactly they are doing when you
8 matches
Mail list logo
