Local Regression - Degree of Local Polynomials

Degree of Local Polynomials

The local polynomials fit to each subset of the data are almost always of first or second degree; that is, either locally linear (in the straight line sense) or locally quadratic. Using a zero degree polynomial turns LOESS into a weighted moving average. Such a simple local model might work well for some situations, but may not always approximate the underlying function well enough. Higher-degree polynomials would work in theory, but yield models that are not really in the spirit of LOESS. LOESS is based on the ideas that any function can be well approximated in a small neighborhood by a low-order polynomial and that simple models can be fit to data easily. High-degree polynomials would tend to overfit the data in each subset and are numerically unstable, making accurate computations difficult.

Read more about this topic:  Local Regression

Famous quotes containing the words degree of, degree and/or local:

    “I never saw, heard, nor read, that the clergy were beloved in any nation where Christianity was the religion of the country. Nothing can render them popular, but some degree of persecution.”
    —Jonathan Swift (1667–1745)

    “I began to realize that it was bigotry of the worst kind to say that it’s better to be dead than to be born retarded or blind or without a limb. It’s a value judgment you’re making about someone’s life, based on their degree of perfection.”
    —Juli Loesch (b. c. 1953)

    “Hey, you dress up our town very nicely. You don’t look out the Chamber of Commerce is going to list you in their publicity with the local attractions.”
    —Robert M. Fresco, and Jack Arnold. Dr. Matt Hastings (John Agar)