Weighted Least Squares

Weighted Least Squares
As a first step, one may wish to keep the assumption about the uncorrelatedness of the errors, and just allow the variance of the errors not to be the same across the range of the predictors.

Weighted Least Squares. In addition to least squares and absolute deviation regression (see above), weighted least squares estimation is probably the most commonly used technique.

Iteratively Reweighted Least Squares A method for maximum likelihood estimation of a generalized linear model. It is equivalent to Newton-Raphson optimization. See McCullagh&Nelder.

Simple linear regression Â- Ordinary least squares Â- Generalized least squares Â- Weighted least squares Â- General linear model
Predictor structure
Polynomial regression Â- Growth curve Â- Segmented regression Â- Local regression ...

The 6-plot is a collection of 6 specific graphical techniques whose purpose is to assess the validity of a Y versus X fit. The fit can be a linear fit, a non-linear fit, a LOWESS (locally weighted least squares) fit, a spline fit, ...

See also: Distribution, Regression, Variance, Estimation, Residual