使用线性回归对数据子集输出R平方

Question

I have a dataset with lag , psit , and var as variables.

set.seed(560)
df<-data.frame(lag= rep(1:40, each=228), psit= rep(rnorm(228, 20, 
10)),var=rnorm(9120, 50, 10))

For each subset of lag I would like to run a linear regression where psit is predicted by var lm(psit~var, df) . I would like to output the R-squared value, the F-statistic and the p-value for the model into a datatframe.

output<-data.frame(lag= rep(1:40, each=1), rsqrd= rep(rnorm(40, .5, 
0.01)),fstat=rnorm(40,5, 0.05), pvalue=rnorm(40,0.01, 0.1))

I have tried:

models <- 
  df %>%
  group_by(lag) %>%
  do(model = lm(psit ~ var,data = .))


rsqrd<- 
  model %>%
  do(data.frame(
   lag = .$lag,
    summary(.)$r.squared, summary(.)$fstatistic,summary(.)$pvalue))

Answer 1

You can use the broom library's glance function to get the summary statistics you want from a series of linear models:

library(broom)
rsqrd <- 
    models %>%
    ungroup() %>% group_by(lag) %>%
    do(glance(.$model[[1]]))

glance takes a single linear model and returns a one-row data frame of summary statistics.