Use cross validation on linear regression

Hey!

I have to fit a linear (general and multiple) model to my data and use leave one out cross validation on the model. I would like to compute the training error, test error and the generalization error and plot the errors as a function of the used models. My data is two 1x53 vectors.

I have tried a lot of things, but I am confused of what the right way to do this is. Can you help me?