R - Saving Variable to dataframe from own function

Question

again I'm stuck...

I want to write a function to get several statistics for checking the assumptions for a linear regression. The function I'm quoting is not yet done, but I think you'll get the point:

check.regression <- function(regmodel, dataframe, resplots = TRUE,
                             durbin = TRUE, savecheck = TRUE) {
     print(dwt(regmodel)) # Durbin-Watson-Test
     dataframe$stand.res <- rstandard(regmodel) # Saving Standardized Residuals                   
}

As you see, I want to save the standardized residuals of the model into the given dataframe.

regmodel refers to the model computed by the linear regression lm( y~x) and dataframe is the name of the dataframe from which the regression model is computed.

The problem is: nothing is saved within my function. If I do the command without the function, the residuals are properly saved into my dataframe.

I guess, there has to be something like

save(dataframe$stand.res <- rstandard(regmodel))

as I also have to specify plotting or writing things to the console within a function, but I don't know how that command might be.

Any ideas?

flodel · Accepted Answer · 2013-08-30 10:49:54Z

4

R uses pass-by-value so what is sent to the function is a copy of your data.frame. (sort of, passing on some details.)

So when you call the function, you need to 1) return the modified data.frame and 2) assign it or you will lose the results.

check.regression <- function(regmodel, dataframe, resplots = TRUE,
                             durbin = TRUE, savecheck = TRUE) {
     print(dwt(regmodel)) # Durbin-Watson-Test
     dataframe$stand.res <- rstandard(regmodel) # Saving Standardized Residuals
     return(dataframe)                  
}

dataframe <- check.regression(regmodel, dataframe)

edited Aug 30, 2013 at 10:49

answered Aug 30, 2013 at 10:03

flodel

89.3k21 gold badges190 silver badges225 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

deschen Over a year ago

Sorry, now I get it. I overlooked the ende of your reply (dataframe <- check.regression(regmodel, dataframe))! With this command, everything works well. Thanks!

Collectives™ on Stack Overflow

R - Saving Variable to dataframe from own function

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related