Save beta coefficients for each independent variable in "ols_all_subset()"

[TimmyKarl]

When running the 'ols_all_subset'-function, it would be nice to be able to save the beta-coefficients for each independent variable in each regression.

What I want to achieve is to be able to average the coefficients for every independent variable. So lets say I have 9 independent variables. In total, there will be 511 different regression models. Each variable was included in 256 models. I want to average these 256 beta-coefficients.

[aravindhebbali]

Hi @TimmyKarl , I have added a new function ols_all_subset_betas() which will return the coefficient for each independent variable from each regression.

library(olsrr)
library(dplyr)

# model
model <- lm(mpg ~ disp + hp + wt, data = mtcars)

# all possible regression 
ols_all_subset(model)
# A tibble: 7 x 6
  Index     N Predictors `R-Square` `Adj. R-Square` `Mallow's Cp`
  <int> <int>      <chr>      <chr>           <chr>         <chr>
1     1     1         wt    0.75283         0.74459      11.96609
2     2     1       disp    0.71834         0.70895      17.54291
3     3     1         hp    0.60244         0.58919      36.28451
4     4     2      hp wt    0.82679         0.81484       2.00820
5     5     2    disp wt    0.78093         0.76582       9.42277
6     6     2    disp hp    0.74824         0.73088      14.70870
7     7     3 disp hp wt    0.82684         0.80828       4.00000

# beta-coefficients for each independent variable in each regression
betas <- ols_all_subset_betas(model)
betas
# A tibble: 19 x 3
   model   predictor          beta
   <int>       <chr>         <dbl>
 1     1 (Intercept) 29.5998547562
 2     1        disp -0.0412151200
 3     2 (Intercept) 30.0988605396
 4     2          hp -0.0682282781
 5     3 (Intercept) 37.2851261673
 6     3          wt -5.3444715727
 7     4 (Intercept) 30.7359042483
 8     4        disp -0.0303462766
 9     4          hp -0.0248400812
10     5 (Intercept) 34.9605540362
11     5        disp -0.0177247443
12     5          wt -3.3508253333
13     6 (Intercept) 37.2272701164
14     6          hp -0.0317729470
15     6          wt -3.8778307424
16     7 (Intercept) 37.1055052690
17     7        disp -0.0009370091
18     7          hp -0.0311565508
19     7          wt -3.8008905826

#  average the coefficients for every independent variable
betas %>%
  select(predictor, beta) %>%
  group_by(predictor) %>%
  summarise_all(mean)
# A tibble: 4 x 2
    predictor        beta
        <chr>       <dbl>
1 (Intercept) 33.85901073
2        disp -0.02255579
3          hp -0.03899946
4          wt -4.09350456