Page 400 - Applied Statistics with R
P. 400
400 CHAPTER 16. VARIABLE SELECTION AND MODEL BUILDING
summary(hipcenter_mod_forw_aic)$adj.r.squared
## [1] 0.6533055
summary(hipcenter_mod_forw_bic)$adj.r.squared
## [1] 0.6282374
2
We can compare the two selected models’ Adjusted as well as their LOOCV
RMSE The results are very similar to those using backwards selection, although
the models are not exactly the same.
calc_loocv_rmse(hipcenter_mod)
## [1] 44.44564
calc_loocv_rmse(hipcenter_mod_forw_aic)
## [1] 37.62516
calc_loocv_rmse(hipcenter_mod_forw_bic)
## [1] 37.2511
16.2.3 Stepwise Search
Stepwise search checks going both backwards and forwards at every step. It
considers the addition of any variable not currently in the model, as well as the
removal of any variable currently in the model.
Here we perform stepwise search using AIC as our metric. We start with
the model hipcenter ~ 1 and search up to hipcenter ~ Age + Weight +
HtShoes + Ht + Seated + Arm + Thigh + Leg. Notice that at many of the
steps, some row begin with -, while others begin with +.
hipcenter_mod_both_aic = step(
hipcenter_mod_start,
scope = hipcenter ~ Age + Weight + HtShoes + Ht + Seated + Arm + Thigh + Leg,
direction = "both")

