βœ… Quiz M7.02#

Question

Given a dataset containing records from patients in 10 different hospitals, we would like to predict if a patient has a disease or not. We suspect that different hospitals can have systematic biases in their respective populations (age, socioeconomic status, genetics…). Which cross-validation strategies are the most adequate to evaluate the ability of the model to make good predictions on patients from unseen hospitals.

  • a) Group stratified k-fold cross-validation

  • b) Group k-fold

  • c) Stratified k-fold cross-validation

  • d) Leave-one-out cross-validation

Select all answers that apply