How to get r.squared for each regression?

问题

Im working with a huge data frame with structure similar to the followings. I use output_reg to store slope and intercept for each treatment but I need to add r.squared for each lm (y~x) and store it in another column besides the other two. Any hint on that?

library(plyr)

field <- c('t1','t1','t1', 't2', 't2','t2', 't3', 't3','t3')
predictor <- c(4.2, 5.3, 5.4,6, 7,8.5,9, 10.1,11)
response <- c(5.1, 5.1, 2.4,6.1, 7.7,5.5,1.99, 5.42,2.5)
my_df <- data.frame(field, predictor, response, stringsAsFactors = F)

 output_reg<-list() 
  B<-(unique(my_df$field))
  for (i in 1:length(B)) {
  index <- my_df[my_df$field==B[i],]
 x<- index$predictor
 y<- index$response
output_reg[[i]] <- lm (y ~ x) #  gets estimates for each field
}

Thanks

回答1:

r.squared can be accessed via the summary of the model, try this:

m <- lm(y ~ x)
rs <- summary(m)$r.squared

The summary object of the linear regression result contains almost everything you need:

output_reg<-list() 
B<-(unique(my_df$field))
for (i in 1:length(B)) {
    index <- my_df[my_df$field==B[i],]
    x<- index$predictor
    y<- index$response
    m <- lm (y ~ x)
    s <- summary(m)            # get the summary of the model
    # extract every thing you need from the summary object
    output_reg[[i]] <- c(s$coefficients[, 'Estimate'], r.squared = s$r.squared) 
} 
output_reg
#[[1]]
#(Intercept)           x   r.squared 
# 10.7537594  -1.3195489   0.3176692 

#[[2]]
#(Intercept)           x   r.squared 
#  8.8473684  -0.3368421   0.1389040 

#[[3]]
#(Intercept)           x   r.squared 
#-0.30500000  0.35963455  0.03788593

To bind the result together:

do.call(rbind, output_reg)
#      (Intercept)          x  r.squared
# [1,]   10.753759 -1.3195489 0.31766917
# [2,]    8.847368 -0.3368421 0.13890396
# [3,]   -0.305000  0.3596346 0.03788593

回答2:

Check-out the broom package and sprinkle in some dplyr (see this vignette):

library(broom)
library(dplyr)

my_df %>%
  group_by(field) %>%
  do(glance(lm(predictor ~ response, data = .))) #also see do(tidy(...))

#   field  r.squared adj.r.squared     sigma  statistic   p.value    df    logLik       AIC       BIC deviance df.residual
#   <chr>      <dbl>         <dbl>     <dbl>      <dbl>     <dbl> <int>     <dbl>     <dbl>     <dbl>    <dbl>       <int>
# 1    t1 0.31766917    -0.3646617 0.7778175 0.46556474 0.6188153     2 -1.855107  9.710214  7.006051 0.605000           1
# 2    t2 0.13890396    -0.7221921 1.6513038 0.16131065 0.7568653     2 -4.113593 14.227185 11.523022 2.726804           1
# 3    t3 0.03788593    -0.9242281 1.3894755 0.03937779 0.8752903     2 -3.595676 13.191352 10.487189 1.930642           1

Alternatively, save the regressions first:

regressions <- my_df %>% group_by(field) %>% do(fit = lm(predictor ~ response, data = .))

regressions %>% tidy(fit)
regressions %>% glance(fit)

回答3:

You can do the following using purrr

require(purrr)
my_df %>% 
  slice_rows("field") %>% 
  by_slice(partial(lm, predictor ~ response), .labels = FALSE) %>% 
  flatten %>% 
  map(~c(coef(.), r.squared=summary(.)$r.squared))

Which gives you:

[[1]]
(Intercept)    response   r.squared 
  5.9777778  -0.2407407   0.3176692 

[[2]]
(Intercept)    response   r.squared 
  9.8195876  -0.4123711   0.1389040 

[[3]]
(Intercept)    response   r.squared 
 9.68534163  0.10534562  0.03788593

If you want a data.frame back instead use this as last line:

map_df(~as.data.frame(t(c(coef(.), r.squared=summary(.)$r.squared))))

回答4:

You can create a data frame with model stats like this:

model_stats <-   data.frame(model$coefficients)
model_stats <- rbind(model_stats,  r.sq = summary(model)$r.squared)

来源：https://stackoverflow.com/questions/39354532/how-to-get-r-squared-for-each-regression

标签

dataframe

plyr

stat