Statistic - Smooth (Function Continuity) (Soft ?)


To smooth a data set is to create an approximating function that attempts to capture important patterns in the data, while leaving out noise.

In mathematical analysis, smoothness has to do with how many derivatives of a function exist and are continuous. The term smooth function is often used technically to mean a function that has derivatives of all orders everywhere in its domain. ie Smoothed conditional means. See smoothness


Data smoothing is typically done through the simplest of all density estimators, the histogram.

loess and cubic smoothing splines are probably the two best ways of doing smoothing.

If you set the degrees of freedom to be equal roughly, they look pretty similar too in general.


Documentation / Reference

Powered by ComboStrap