Model evaluation

Practicing Statistics Interview Questions in R

Zuzanna Chmielewska

Actuary

Cross-validation

Cross-validation

Cross-validation

Cross-validation

Cross-validation

Cross-validation

Cross-validation

Confusion matrix

Confusion matrix

Confusion matrix

Confusion matrix

Classification metrics

$\text{accuracy} = \frac{TP+TN}{TP+TN+FP+FN}$

$\text{precision} = \frac{TP}{TP+FP}$

$\text{recall} = \frac{TP}{TP+FN}$

Classification metrics

Precision

Recall

Regression metrics

Regression metrics

Regression metrics

Root Mean Squared Error

$RMSE = \sqrt{\frac{1}{n}\sum_{i=1}^{n} (y_i - \hat{y}_i)^2}$

Mean Absolute Error

$MAE = \frac{1}{n} \sum_{i=1}^{n} |y_i - \hat{y}_i|$

Regression metrics

Root Mean Squared Error

$RMSE = \sqrt{\frac{1}{n}\sum_{i=1}^{n} (y_i - \hat{y}_i)^2}$

• high weight to large errors

Mean Absolute Error

$MAE = \frac{1}{n} \sum_{i=1}^{n} |y_i - \hat{y}_i|$

• straightforward interpretation

Summary

• validation set approach
• cross-validation
• confusion matrix
• classification metrics
• regression metrics

Let's practice!

Practicing Statistics Interview Questions in R