Back to Lexicon


\ ˈoʊvər-ˈfɪtɪŋ \

The production of a statistical model that fits too closely to a given set of data.

A model that is over-fitted to its underlying data set will incorporate any random noise present in that data set. This is likely to result in the model providing a poor fit to other data sets and poor predictions for future observations.

Keep exploring our Lexicon of Longevity
Back to Lexicon