Comparing an isotonic model to an additive model

35 Views Asked by At

Say I have a dataset in $x,y$, and say I fit a few different models to the dataset. Examples could be an isotonic regression, a smoothing spline and a simple linear regression. What are some ways I can determine which of the fits is best besides looking at graphs and going with what "feels right"? I was thinking of using something based around RSS but am unsure on the specifics.