[R] Problem with Anova() in package car

2015-01-13 Thread Gang Chen
I'm having some trouble with Anova() in package car. When the model
formula is explicitly expressed:

library('nlme')
library('car')
fm - lme(distance ~ age + Sex, data = Orthodont, random = ~ 1)

Anova() works fine:

Anova(fm)

However, if the model formula is scanned from an external source:

myModel - as.formula(distance ~ age + Sex)
fm2 - lme(myModel, data = Orthodont, random = ~ 1)

I get the following error:

Anova(fm2)
Error: object of type 'symbol' is not subsettable

How to resolve the situation when the model formula is defined externally?

Thanks,
Gang

__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.


Re: [R] Problem with Anova() in package car

2015-01-13 Thread Gang Chen
Dear John,

Thanks a lot for the quick response and fix! I'm looking forward to
try out the development version. I assume that the fix will be
released in the official version at some point.

Thanks again,
Gang

On Tue, Jan 13, 2015 at 5:06 PM, John Fox j...@mcmaster.ca wrote:
 Dear Gang,

 The problem was in the model.matrix.lme() method provided by the car
 package, and is now fixed in the development version of the car package on
 R-Forge. You should be able to install it from there via
 install.packages(car, repos=http://R-Forge.R-project.org;) after the
 package is next built on R-Forge, usually in a day or so.

 Best,
  John

 -Original Message-
 From: R-help [mailto:r-help-boun...@r-project.org] On Behalf Of Gang Chen
 Sent: January-13-15 1:48 PM
 To: r-help
 Subject: [R] Problem with Anova() in package car

 I'm having some trouble with Anova() in package car. When the model
 formula is explicitly expressed:

 library('nlme')
 library('car')
 fm - lme(distance ~ age + Sex, data = Orthodont, random = ~ 1)

 Anova() works fine:

 Anova(fm)

 However, if the model formula is scanned from an external source:

 myModel - as.formula(distance ~ age + Sex)
 fm2 - lme(myModel, data = Orthodont, random = ~ 1)

 I get the following error:

 Anova(fm2)
 Error: object of type 'symbol' is not subsettable

 How to resolve the situation when the model formula is defined externally?

 Thanks,
 Gang

 __
 R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
 https://stat.ethz.ch/mailman/listinfo/r-help
 PLEASE do read the posting guide http://www.R-project.org/posting-
 guide.html
 and provide commented, minimal, self-contained, reproducible code.


 ---
 This email has been checked for viruses by Avast antivirus software.
 http://www.avast.com


__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.


Re: [R] Problem with Anova() in package car

2015-01-13 Thread John Fox
Dear Gang,

The problem was in the model.matrix.lme() method provided by the car
package, and is now fixed in the development version of the car package on
R-Forge. You should be able to install it from there via
install.packages(car, repos=http://R-Forge.R-project.org;) after the
package is next built on R-Forge, usually in a day or so.

Best,
 John

 -Original Message-
 From: R-help [mailto:r-help-boun...@r-project.org] On Behalf Of Gang Chen
 Sent: January-13-15 1:48 PM
 To: r-help
 Subject: [R] Problem with Anova() in package car
 
 I'm having some trouble with Anova() in package car. When the model
 formula is explicitly expressed:
 
 library('nlme')
 library('car')
 fm - lme(distance ~ age + Sex, data = Orthodont, random = ~ 1)
 
 Anova() works fine:
 
 Anova(fm)
 
 However, if the model formula is scanned from an external source:
 
 myModel - as.formula(distance ~ age + Sex)
 fm2 - lme(myModel, data = Orthodont, random = ~ 1)
 
 I get the following error:
 
 Anova(fm2)
 Error: object of type 'symbol' is not subsettable
 
 How to resolve the situation when the model formula is defined externally?
 
 Thanks,
 Gang
 
 __
 R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
 https://stat.ethz.ch/mailman/listinfo/r-help
 PLEASE do read the posting guide http://www.R-project.org/posting-
 guide.html
 and provide commented, minimal, self-contained, reproducible code.


---
This email has been checked for viruses by Avast antivirus software.

__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.