A colleague is assessing a regression model using only the Adjusted R-Squared. What considerations or additional metrics might you suggest, and why?

  • Include MAE; because it's less sensitive to outliers
  • Include MSE; because it's the standard metric
  • Include RMSE; because it's more interpretable
  • Include both RMSE and MAE; for a more comprehensive assessment
While Adjusted R-Squared is useful, including both Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) provides a more comprehensive assessment. RMSE can help in understanding how the model is penalizing larger errors, and MAE can give an indication of the model's sensitivity to outliers. Together, they offer a more nuanced view of the model's performance.
Add your answer
Loading...

Leave a comment

Your email address will not be published. Required fields are marked *