R help - Sep 2006 - extract data from lm object and then use again?

Hi list,

I want to write a general function so that it would take an lm object,
extract its data element, then use the data at another R function (eg, glm).
I searched R-help list, and found this would do the trick of the first part:
a.lm$call$data
this would return a name object but could not be recognized as a
data.frameby glm. I also tried
call(as.character(a.lm$call$data))
or
eval(call(as.character(a.lm$call$data)))
neither works.

By eval(call(...)), it acts as evaluating of a function, but what I want is
just a data frame object which could be inserted into glm function. Anyone
could help? Thanks,

Mike

	[[alternative HTML version deleted]]

Hi,

the data of the model fit is stored in lm$model and should work....

Good luck,
Thilo

On Friday 22 September 2006 16:45, Mike Wolfgang wrote:
> Hi list,
>
> I want to write a general function so that it would take an lm object,
> extract its data element, then use the data at another R function (eg,
> glm). I searched R-help list, and found this would do the trick of the
> first part: a.lm$call$data
> this would return a name object but could not be recognized as a
> data.frameby glm. I also tried
> call(as.character(a.lm$call$data))
> or
> eval(call(as.character(a.lm$call$data)))
> neither works.
>
> By eval(call(...)), it acts as evaluating of a function, but what I want is
> just a data frame object which could be inserted into glm function. Anyone
> could help? Thanks,
>
> Mike
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> 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.
-- 
________________________
Thilo Kellermann
Department of Psychiatry und Psychotherapy
RWTH Aachen University
Pauwelstr. 30
52074 Aachen
Tel.: +49 (0)241 / 8089977
Fax.: +49 (0)241 / 8082401
E-Mail: tkellermann at ukaachen.de

On Fri, 2006-09-22 at 10:45 -0400, Mike Wolfgang wrote:
> Hi list,
> 
> I want to write a general function so that it would take an lm object,
> extract its data element, then use the data at another R function (eg,
glm).
> I searched R-help list, and found this would do the trick of the first
part:
> a.lm$call$data
> this would return a name object but could not be recognized as a
> data.frameby glm. I also tried
> call(as.character(a.lm$call$data))
> or
> eval(call(as.character(a.lm$call$data)))
> neither works.
> 
> By eval(call(...)), it acts as evaluating of a function, but what I want is
> just a data frame object which could be inserted into glm function. Anyone
> could help? Thanks,
> 
> Mike
If the 'data' argument in lm() is used, then this approach could work:
> Iris2 <- eval(lm(Sepal.Length ~ Species, data = iris)$call$data)
> str(Iris2)
`data.frame':   150 obs. of  5 variables:
 $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
 $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
 $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 $ Species     : Factor w/ 3 levels
"setosa","versicolor",..: 1 1 1 1 1
1 1 1 1 1 ...


However, note that you do not get the actual data used within the lm()
function (the model frame) but the entire source data frame.

What you likely want instead is the model frame containing the columns
actually used in the model formula:
> Iris3 <- lm(Sepal.Length ~ Species, data = iris)$model
> str(Iris3)
`data.frame':   150 obs. of  2 variables:
 $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 $ Species     : Factor w/ 3 levels
"setosa","versicolor",..: 1 1 1 1 1
1 1 1 1 1 ...
 - attr(*, "terms")=Classes 'terms', 'formula' length
3 Sepal.Length ~
Species
  .. ..- attr(*, "variables")= language list(Sepal.Length, Species)
  .. ..- attr(*, "factors")= int [1:2, 1] 0 1
  .. .. ..- attr(*, "dimnames")=List of 2
  .. .. .. ..$ : chr [1:2] "Sepal.Length" "Species"
  .. .. .. ..$ : chr "Species"
  .. ..- attr(*, "term.labels")= chr "Species"
  .. ..- attr(*, "order")= int 1
  .. ..- attr(*, "intercept")= int 1
  .. ..- attr(*, "response")= int 1
  .. ..- attr(*, ".Environment")=length 15 <environment>
  .. ..- attr(*, "predvars")= language list(Sepal.Length, Species)
  .. ..- attr(*, "dataClasses")= Named chr [1:2] "numeric"
"factor"
  .. .. ..- attr(*, "names")= chr [1:2] "Sepal.Length"
"Species"


HTH,

Marc Schwartz

On Fri, 22 Sep 2006, Thilo Kellermann wrote:
> Hi,
>
> the data of the model fit is stored in lm$model and should work....
>
Not reliably. In the first place, you should use the accessor function 
model.frame(model) rather than model$model, which works even if the model 
was fitted with model=FALSE.

But even then,
   glm(formula(model), data=model.frame(model))
will not work reliably.
Consider
   model <- lm(log(Volume)~log(Height)+log(Girth),data=trees)

The model frame has variables called eg "log(Volume)" rather than 
"Volume".

When you need the source data frame you need to do something like
    eval(model$call$data, environment(formula(model)))
and even this might not work, eg if the model had no data 
argument.

However, if the model had no data argument then the variables 
must be available in environment(formula(model)), in which case any data 
frame of the right size will do.

If there are no missing observations or the model  was fitted with 
na.action="na.exclude" then a fairly reliable approach is to use
   eval(model$call$data, environment(formula(model)))
if it is not NULL and to fall back to model.frame(model). This is what 
termplot() does.


 	-thomas