I think your idea to remove the warnings is excellent, and a good compromise. Characters
already work fine in modeling functions except for the silly warning.
It is interesting how often the defaults for a program reflect the data sets in use at the
time the defaults were chosen. There are so
Note that changing this does not just mean getting rid of "silly warnings".
Currently, predict.lm() can give wrong answers when stringsAsFactors is FALSE.
> d <- data.frame(x=1:10, f=rep(c("A","B","C"), c(4,3,3)), y=c(1:4, 15:17,
28.1,28.8,30.1))
> fit_ab <- lm(y ~ x + f, data = d, subset = f
On 11/02/2013 12:13 PM, William Dunlap wrote:
Note that changing this does not just mean getting rid of "silly warnings".
Currently, predict.lm() can give wrong answers when stringsAsFactors is FALSE.
> d <- data.frame(x=1:10, f=rep(c("A","B","C"), c(4,3,3)), y=c(1:4, 15:17,
28.1,28.8,30.1))
The root of this problem is that the .getXlevels function does not return the levels for
character variables.
Future predictions depend on that information.
On 02/11/2013 11:50 AM, Duncan Murdoch wrote:
On 11/02/2013 12:13 PM, William Dunlap wrote:
Note that changing this does not just mean ge
On 2/11/2013 5:50 AM, Terry Therneau wrote:
I think your idea to remove the warnings is excellent, and a good
compromise. Characters already work fine in modeling functions except
for the silly warning.
It is interesting how often the defaults for a program reflect the data
sets in use at the t
On 11/02/2013 2:34 PM, Terry Therneau wrote:
The root of this problem is that the .getXlevels function does not return the
levels for
character variables.
Thanks, that looks easy to fix (not by changing .getXlevels, but by
having model.frame convert the character variables, instead
of waiting
On Feb 11, 2013, at 18:50 , Duncan Murdoch wrote:
>
> I do think that it's unfortunate that we don't get the same result in both
> cases, and I'd like to have gotten the predictions you suggested, but I don't
> think that's going to happen. The reason for the difference is that the
> subsett
Peter,
I had an earlier response to Duncan that I should have copied to the list.
The subset issue can be fixed. When the model changes character to factor, it needs to
remember the levels; just like it does with the factors. We are simply seeing a reprise
of problems that occured whem mode
