In terms of calculating cross-validation, how many times is the model fitted in LOOCV?

In Leave-One-Out Cross-Validation (LOOCV), the model is fitted N times, where N is the number of observations in the dataset. This method entails that for each iteration, one data point is left out as the validation set while the remaining N-1 data points are used to train the model. This process is repeated until each individual data point has been used as the validation set exactly once. As a result, if there are N observations, the model fitting occurs N separate times, creating a robust estimate of the model's performance.

This approach contrasts with other cross-validation techniques, such as k-fold cross-validation, where the data is divided into k subsets and the model is fitted k times. In LOOCV, since every data point is left out one at a time, it guarantees that the model is rigorously evaluated against every single data point in the dataset.