202412111238
Status: #idea
Tags:
State: #nascient
Resampling Methods
It consists of fitting the same model to different subsets of the training data multiple times in the pursuit of better understanding the model or getting a better idea for the fit/variance/whatnot of the estimated parameters.
It is a computational method that can help us empirically compute the mean and variance of models and parameters in situations where there is no closed-form solution to do so.
There are two main ones:
Cross Validation
Bootstrap