cv_error() computes the root mean squared error from a model fitted
to kfold cross-validated test-training-data. cv_compare()
does the same, for multiple formulas at once (by calling cv_error()
for each formula).
cv_error(data, formula, k = 5)
cv_compare(data, formulas, k = 5)A data frame.
The formula to fit the linear model for the test and training data.
The number of folds for the kfold-crossvalidation.
A list of formulas, to fit linear models for the test and training data.
A data frame with the root mean squared errors for the training and test data.
cv_error() first generates cross-validated test-training pairs, using
crossv_kfold and then fits a linear model, which
is described in formula, to the training data. Then, predictions
for the test data are computed, based on the trained models.
The training error is the mean value of the rmse for
all trained models; the test error is the rmse based on all
residuals from the test data.
data(efc)
cv_error(efc, neg_c_7 ~ barthtot + c161sex)
#> Warning: unnest() has a new interface. See ?unnest for details.
#> Try `df %>% unnest(c(predicted, residuals))`, with `mutate()` if needed
#> model train.error test.error
#> 1 neg_c_7 ~ barthtot + c161sex 3.5069 3.5186
cv_compare(efc, formulas = list(
neg_c_7 ~ barthtot + c161sex,
neg_c_7 ~ barthtot + c161sex + e42dep,
neg_c_7 ~ barthtot + c12hour
))
#> Warning: unnest() has a new interface. See ?unnest for details.
#> Try `df %>% unnest(c(predicted, residuals))`, with `mutate()` if needed
#> Warning: unnest() has a new interface. See ?unnest for details.
#> Try `df %>% unnest(c(predicted, residuals))`, with `mutate()` if needed
#> Warning: unnest() has a new interface. See ?unnest for details.
#> Try `df %>% unnest(c(predicted, residuals))`, with `mutate()` if needed
#> model train.error test.error
#> 1 neg_c_7 ~ barthtot + c161sex 3.5065 3.5223
#> 2 neg_c_7 ~ barthtot + c161sex + e42dep 3.4859 3.5096
#> 3 neg_c_7 ~ barthtot + c12hour 3.5024 3.5252