Perhaps the two of you would like to submit a patch for consideration?
I think you can take it that it was considered in Dec 2002 and no one
wanted to do the work to check the feasibility.
The form in Open Source projects is that those who want a feature
implement it and offer it to the
I'm trying to cross-compile R on a Mac OS X box to target Win32. It
works quite well, everything works, except for one fortran file ppr.f
in the stats package:
-- Making package stats
adding build stamp to DESCRIPTION
installing NAMESPACE file and metadata
making DLL
Full_Name: Tanya Logvinenko
Version: 1.7.0
OS: Windows 2000
Submission from: (NULL) (132.183.156.125)
For unbalanced design, I ran into problem with ANOVA (aov function). The sum of
squares for only for the second factor and total are computed correctly, but sum
of squares for the first factor
On a related topic, a client came up with this example
a few days ago which I was unable to explain. (But he
did heed my advise of don't do that.)
matrixObj - array(1:4, c(2,2))
class(matrixObj) - matrix
fooObj - matrixObj
class(fooObj) - foo
fooObj[1:2]
Testing
[,1] [,2]
[1,]13
It is not a bug. It is supposed to be that way. It is even a FAQ.
-thomas
On Thu, 29 Jul 2004 [EMAIL PROTECTED] wrote:
Full_Name: Tanya Logvinenko
Version: 1.7.0
OS: Windows 2000
Submission from: (NULL) (132.183.156.125)
For unbalanced design, I ran into problem with ANOVA (aov
Suggest you try R 1.9.1 patched. This is what I get on
Windows XP with that:
matrixObj - array(1:4, c(2,2))
class(matrixObj) - matrix
fooObj - matrixObj
class(fooObj) - foo
fooObj[1:2]
[1] 1 2
matrixObj[1:2]
[1] 1 2
getAnywhere([.matrix)
no object named '[.matrix' was found
What do you think is the correct answer and on what authority?
(These are explicitly sequential aka Type 1 anova tables.)
That the SSqs depend on the order of fitting is a feature of an unbalanced
design. I believe that R is correct and your understanding is not.
On Thu, 29 Jul 2004 [EMAIL