I have mostly been using stargazer
for comparing linear model summaries but there are few other packages that also provide this feature.
One in particular is the library(memisc)
. memisc
was designed for survey data sets but it can handle other kinds, too.
Below, I’ve put togehter an example that utilzes mtcars
data with memisc
to provide a comparison of stats between linear models (lm
s).
First we load the library, and create the linear models:
library(memisc) # mtcars
lm0 <- lm(hp ~ wt, mtcars)
lm1 <- lm(qsec ~ hp, mtcars)
lm2 <- lm(qsec ~ wt, mtcars)
Next, we use mtable
to list the models to compare. Included is the argument summary.stats
that can be populated with a charcater vector with the names of the summary stats to report:
mtable123 <- mtable('Model 1' = lm0,
'Model 2' = lm1,
'Model 3' = lm2,
summary.stats = c('R-squared','F','p','N'))
And then we print out the table:
mtable123
##
## Calls:
## Model 1: lm(formula = hp ~ wt, data = mtcars)
## Model 2: lm(formula = qsec ~ hp, data = mtcars)
## Model 3: lm(formula = qsec ~ wt, data = mtcars)
##
## =================================================
## Model 1 Model 2 Model 3
## ----------- ---------- ----------
## hp qsec qsec
## -------------------------------------------------
## (Intercept) -1.821 20.556*** 18.875***
## (32.325) (0.542) (1.103)
## wt 46.160*** -0.319
## (9.625) (0.328)
## hp -0.018***
## (0.003)
## -------------------------------------------------
## R-squared 0.434 0.502 0.031
## F 22.999 30.190 0.945
## p 0.000 0.000 0.339
## N 32 32 32
## =================================================
You can also use array-semantics to access portions of the data which is a nice touch:
mtable123 <- mtable("Model 1"=lm0,"Model 2"=lm1,"Model 3"=lm2,
summary.stats=c("sigma","R-squared","F","p","N"))
mtable123[c("wt","hp"),
c("Model 2","Model 3")]
##
## Calls:
## Model 2: lm(formula = qsec ~ hp, data = mtcars)
## Model 3: lm(formula = qsec ~ wt, data = mtcars)
##
## =================================
## Model 2 Model 3
## ---------------------------------
## wt -0.319
## (0.328)
## hp -0.018***
## (0.003)
## ---------------------------------
## sigma 1.282 1.789
## R-squared 0.502 0.031
## F 30.190 0.945
## p 0.000 0.339
## N 32 32
## =================================