Ben Bolker bbol...@gmail.com
on Wed, 23 Feb 2011 19:36:43 -0500 writes:
On 11-02-23 06:12 PM, Prof Brian Ripley wrote:
residuals() and $residuals are often very different:
residuals() is generic, but even the default method is *not*
simple extraction. Their values can be
By changing three lines in drop1 from access based on $ to access
based on standard accessor methods (terms() and residuals()), it becomes
*much* easier to extend drop1 to work with other model types.
The use of $ rather than accessors in this context seems to be an
oversight rather than a
Ben Bolker bbol...@gmail.com
on Wed, 23 Feb 2011 09:14:37 -0500 writes:
By changing three lines in drop1 from access based on $
to access based on standard accessor methods (terms() and
residuals()), it becomes *much* easier to extend drop1 to
work with other model
On 11-02-23 03:20 PM, Martin Maechler wrote:
Ben Bolker bbol...@gmail.com
on Wed, 23 Feb 2011 09:14:37 -0500 writes:
By changing three lines in drop1 from access based on $
to access based on standard accessor methods (terms() and
residuals()), it becomes *much* easier
On Feb 23, 2011, at 21:38 , Ben Bolker wrote:
Potentially, but I am personally much more interested in enabling
drop1(), which seems to be a much more legitimate tool for testing terms
in models than step(), which is so easy to abuse ...
Yes, although repeated use of drop1() easily leads
residuals() and $residuals are often very different: residuals() is
generic, but even the default method is *not* simple extraction. Their
values can be of different lengths: think about an lm fit with
na.action = na.exclude. That is precisely the sort of thing the tests
in add.R were
On 11-02-23 06:12 PM, Prof Brian Ripley wrote:
residuals() and $residuals are often very different: residuals() is
generic, but even the default method is *not* simple extraction. Their
values can be of different lengths: think about an lm fit with na.action
= na.exclude. That is precisely