There are some previous post treating how to validate a logistic regression: Source 1 and Source 2.

But, still, those threads does not answer my question.

Therefore:

If a logistic regression predict probabilities. How can one validate a logistic regression?

Googling I found two ways of validate a model:

1. The first one is by evaluating the confusion matrix (Accuracy, specificity and sensitivity)

2. The second one is by evaluating r, r$^2$ and MAE in different ways such as: (1) Validation Set Approach, (2) Leave one out cross-validation(LOOCV), (3) K-fold cross-Validation, and (4) Repeated K-fold cross-validation. Source 3

Therefore, What is the correct way to validate a logistic regression? By applying option 1 or 2?

There are some previous post treating how to validate a logistic regression: Source 1 and Source 2.

But, still, those threads does not answer my question.

Therefore:

If a logistic regression predict probabilities. How can one validate a logistic regression?

Googling I found two ways of validate a model:

1. The first one is by evaluating the confusion matrix Source3 (Accuracy, specificity and sensitivity)

2. The second one is by evaluating r, r$^2$ and MAE in different ways such as: (1) Validation Set Approach, (2) Leave one out cross-validation(LOOCV), (3) K-fold cross-Validation, and (4) Repeated K-fold cross-validation. Source 4

Therefore, What is the correct way to validate a logistic regression? By applying option 1 or 2?

There are some previous post treating how to validate a logistic regression: Source 1 and Source 2.

But, still, those threads does not answer my question.

Therefore:

If a logistic regression predict probabilities. How can one validate a logistic regression?

Googling I found two ways of validate a model:

1. The first one is by evaluating the confusion matrix (Accuracy, specificity and sensitivity)

2. The second one is by evaluating r, r$^2$ and MAE in different ways such as: (1) Validation Set Approach, (2) Leave one out cross-validation(LOOCV), (3) K-fold cross-Validation, and (4) Repeated K-fold cross-validation. Source 3

Therefore, What is the correct way to evaluate a logistic regression? By applying option 1 or 2?

There are some previous post treating how to validate a logistic regression: Source 1 and Source 2.

But, still, those threads does not answer my question.

Therefore:

If a logistic regression predict probabilities. How can one validate a logistic regression?

Googling I found two ways of validate a model:

1. The first one is by evaluating the confusion matrix (Accuracy, specificity and sensitivity)

2. The second one is by evaluating r, r$^2$ and MAE in different ways such as: (1) Validation Set Approach, (2) Leave one out cross-validation(LOOCV), (3) K-fold cross-Validation, and (4) Repeated K-fold cross-validation. Source 3

Therefore, What is the correct way to validate a logistic regression? By applying option 1 or 2?