Evaluate performance of regression models.
Value
ols_model_performance returns an object of class
"ols_model_performance". An object of class "ols_regress" is a
list containing the following components:
- r
square root of rsquare, correlation between observed and predicted values of dependent variable
- rsq
coefficient of determination or r-square
- adjr
adjusted rsquare
- prsq
predicted rsquare
- aic
akaike information criteria
- sbc
bayesian information criteria
- sbic
sawa bayesian information criteria
- rmse
root mean squared error
Examples
# model
model <- lm(mpg ~ disp + hp + wt, data = mtcars)
# model performance
ols_model_performance(model)
#> Model Performance
#> ---------------------------------------------
#> R 0.909 AIC 158.643
#> R-Squared 0.827 SBC 165.972
#> Adj. R-Squared 0.808 SBIC 68.933
#> Pred R-Squared 0.768 RMSE 2.468
#> ---------------------------------------------
#> AIC: Akaike Information Criteria
#> SBC: Schwarz Bayesian Criteria
#> SBIC: Sawa's Bayesian Criteria
#> RMSE: Root Mean Square Error
#>