R help - Jan 2012 - Calling update on an lm-object inside a function

Dear all,
I want to update an lm (or glm) object by changing the response variable and I
want to do so inside a function. Doing the update outside
of a function is straight forward:
 
 x <- 1:5
 y <- c(1,2,3,3,6)
 mm <- lm(y~x)
 y2 <- c(1,3,3,4,6)
 mm2<- update(mm, y2 ~ .)
 
But I want to make the update inside a function (where the new response variable
is declared
inside the function). If I do 
 
 foo <- function(mod){
   y3 <- c(1,3,3,4,6)
   update(mod, y3 ~ .)
 }
Then I get 
 foo(mm)

Error in eval(expr, envir, enclos) : object 'y3' not found
(because y3 is not known in the global environment - I suppose). To fix this I
do
  
 foo2 <- function(mod){
   y3 <- c(1,3,3,4,6)
   mod2 <- eval(getCall(mod))
   update(mod2, y3 ~ .)
 }
 foo2(mm)

Call:
lm(formula = y3 ~ x)

Coefficients:
(Intercept)            x  
        0.1          1.1  

Question: Is this the "appropriate" way of making such a model
"available" for an update inside a function,
or is there a better way? I guess so - because:
If I change the model formula of my model and then invoke foo2 I get

mm3 <- update(mm,.~.-x)
> foo2(mm3)
Error in eval(expr, envir, enclos) : object 'y3' not found

This puzzles me. Question: can anyone help me clarify why this happens and what
I can do to fix it.

Thanks in advance
S?ren

Dear Soren,

I would try adding the new variable to the dataset and use the data = argument
of lm

foo <- function(mod, data){
   data$y3 <- c(1,3,3,4,6)
   update(mod, y3 ~ ., data = data)
}
x <- 1:5
y <- c(1,2,3,3,6)
dataset <- data.frame(x = x, y = y)
mm <- lm(y~x, data = dataset)
foo(mm, dataset)

Best regards,

Thierry

ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature and
Forest
team Biometrie & Kwaliteitszorg / team Biometrics & Quality Assurance
Kliniekstraat 25
1070 Anderlecht
Belgium
+ 32 2 525 02 51
+ 32 54 43 61 85
Thierry.Onkelinx at inbo.be
www.inbo.be

To call in the statistician after the experiment is done may be no more than
asking him to perform a post-mortem examination: he may be able to say what the
experiment died of.
~ Sir Ronald Aylmer Fisher

The plural of anecdote is not data.
~ Roger Brinner

The combination of some data and an aching desire for an answer does not ensure
that a reasonable answer can be extracted from a given body of data.
~ John Tukey

-----Oorspronkelijk bericht-----
Van: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org]
Namens S?ren H?jsgaard
Verzonden: zondag 22 januari 2012 15:06
Aan: r-help at r-project.org
Onderwerp: [R] Calling update on an lm-object inside a function

Dear all,
I want to update an lm (or glm) object by changing the response variable and I
want to do so inside a function. Doing the update outside of a function is
straight forward:
 
 x <- 1:5
 y <- c(1,2,3,3,6)
 mm <- lm(y~x)
 y2 <- c(1,3,3,4,6)
 mm2<- update(mm, y2 ~ .)
 
But I want to make the update inside a function (where the new response variable
is declared inside the function). If I do
 
 foo <- function(mod){
   y3 <- c(1,3,3,4,6)
   update(mod, y3 ~ .)
 }
Then I get
 foo(mm)

Error in eval(expr, envir, enclos) : object 'y3' not found (because y3
is not known in the global environment - I suppose). To fix this I do
  
 foo2 <- function(mod){
   y3 <- c(1,3,3,4,6)
   mod2 <- eval(getCall(mod))
   update(mod2, y3 ~ .)
 }
 foo2(mm)

Call:
lm(formula = y3 ~ x)

Coefficients:
(Intercept)            x  
        0.1          1.1  

Question: Is this the "appropriate" way of making such a model
"available" for an update inside a function, or is there a better way?
I guess so - because:
If I change the model formula of my model and then invoke foo2 I get

mm3 <- update(mm,.~.-x)
> foo2(mm3)
Error in eval(expr, envir, enclos) : object 'y3' not found

This puzzles me. Question: can anyone help me clarify why this happens and what
I can do to fix it.

Thanks in advance
S?ren

______________________________________________
R-help at r-project.org 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.