ject.org
> Subject: RE: [Rd] vcov and survival
>
> >>>>> Fox, John
> >>>>> on Thu, 14 Sep 2017 13:46:44 + writes:
>
> > Dear Martin, I made three points which likely got lost
> > because of the way I presented them:
>
&
z.ch] Sent: Thursday,
>> September 14, 2017 4:23 AM To: Martin Maechler
>> Cc: Fox, John
>> ; Therneau, Terry M., Ph.D.
>> ; r-devel@r-project.org Subject: Re:
>> [Rd] vcov and survival
>>
>> >>>>> Martin M
On 09/14/2017 08:46 AM, Fox, John wrote:
Dear Martin,
I made three points which likely got lost because of the way I presented them:
(1) Singularity is an unusual situation and should be made more prominent. It
typically reflects a problem with the data or the specification of the model.
Th
> -Original Message-
> From: Therneau, Terry M., Ph.D. [mailto:thern...@mayo.edu]
> Sent: Thursday, September 14, 2017 8:41 AM
> To: Martin Maechler
> Cc: Fox, John ; Therneau, Terry M., Ph.D.
> ; r-devel@r-project.org
> Subject: Re: [Rd] vcov and survival
>
>
> Sent: Thursday, September 14, 2017 4:23 AM
> To: Martin Maechler
> Cc: Fox, John ; Therneau, Terry M., Ph.D.
> ; r-devel@r-project.org
> Subject: Re: [Rd] vcov and survival
>
> >>>>> Martin Maechler
> >>>>> on Thu, 14 Sep 2017 10:13:02 +020
> should get NA rows and columns there. This would require
> eliminating these before e.g. using it in solve(, *) etc,
> but I think it would be a good idea that the useR must deal with
> these NAs actively.
> Shall "we" try and see the fallout in CRAN
I do quite agree that vcov() should be compatible with
> coef() [and summary()] for both 'lm' and 'glm' methods, i.e.,
> should get NA rows and columns there. This would require
> eliminating these before e.g. using it in solve(, *) etc,
> but I thin
this that escapes me.
(for the first one---"no error"--- I gave a reason)
> Best,
> John
> --
> John Fox, Professor Emeritus
> McMaster University
> Hamilton, Ontario, Canada
> Web: socserv.mcmaster.ca/jfox
escapes me.
Best,
John
--
John Fox, Professor Emeritus
McMaster University
Hamilton, Ontario, Canada
Web: socserv.mcmaster.ca/jfox
> -Original Message-
> From: R-devel [mailto:r-devel-boun...@r-project.org] On Behalf Of
> Therneau, Terry M., Ph
I have just noticed a difference in behavior between coxph and lm/glm: if one or more of
the coefficients from the fit in NA, then lm and glm omit that row/column from the
variance matrix; while coxph retains it but sets the values to zero.
Is this something that should be "fixed", i.e., made
10 matches
Mail list logo
