Other Methods
Although the parameters of a regression model are usually estimated using the method of least squares, other methods which have been used include:
- Bayesian methods, e.g. Bayesian linear regression
- Percentage regression, for situations where reducing percentage errors is deemed more appropriate.
- Least absolute deviations, which is more robust in the presence of outliers, leading to quantile regression
- Nonparametric regression, requires a large number of observations and is computationally intensive
- Distance metric learning, which is learned by the search of a meaningful distance metric in a given input space.
Read more about this topic: Regression Estimation
Famous quotes containing the word methods:
“The ancient bitter opposition to improved methods [of production] on the ancient theory that it more than temporarily deprives men of employment ... has no place in the gospel of American progress.”
—Herbert Hoover (1874–1964)
“A writer who writes, “I am alone” ... can be considered rather comical. It is comical for a man to recognize his solitude by addressing a reader and by using methods that prevent the individual from being alone. The word alone is just as general as the word bread. To pronounce it is to summon to oneself the presence of everything the word excludes.”
—Maurice Blanchot (b. 1907)