Print R-squared for all of the models fit with lmList

问题

I used lmList to fit 480 relationships and I would like the R2 of each of these.

Here is an example dataset and model which are pretty close to what it really looks like, except I have 480 eu (experimental units):

eu  mass  day
11  .02    1
11  .03    2
11  .04    3
11  .06    4
12  .01    1
12  .03    2
12  .04    3
12  .05    4

fit<-lmList(mass ~ day | eu, data=df)

Printing fit or summary does not give me the information I want. I am ultimately trying to make a new dataframe that will look like:

eu    intercept    slope    R2
11     .01          .95     .98
12     .01          .96     .98

I've got the coefficients through coef, now I need the R-squared.

回答1:

Here you go:

sapply(fit,function(x) summary(x)$r.squared)
       11        12 
0.9657143 0.9657143 

Or to do everything at once:

sumfun <- function(x) c(coef(x),summary(x)$r.squared)
t(sapply(fit,sumfun))

(you need to transpose the results from sapply to get the table as specified above). Then use names() <- or setNames() to get the column names the way you want them.

回答2:

using Ben Bolker's code, you can make a function that transposes the results and gives the table, all at once:

sumfun <- function(x) 
{
  aux <- function(x) c(coef(x), summary(x)$r.squared)
  t(sapply(x,aux))
}
sumfun(fit)

来源：https://stackoverflow.com/questions/23501852/print-r-squared-for-all-of-the-models-fit-with-lmlist