press {asbio}R Documentation

prediction sum of squares

Description

Calculates PREdiction Sum of Squares (PRESS) for a linear model.

Usage


press(lm, as.R2 = FALSE)

Arguments

lm

An object of class lm.

as.R2

Logical. Whether or not output should be expressed as predicted R2R^2, i.e., PRESS/TSSPRESS/TSS.

Details

The press statistic is calculated as:

i=1ndi2\sum_{i=1}^{n}d_i^2

where

di=ei1hiid_i = \frac{e_i}{1-h_{ii}}

where hiih_{ii} is the ith diagonal element in the hat matrix.

Value

Returns the PRESS statistic.

Author(s)

Ken Aho

References

Kutner, M. H., Nachtsheim, C. J., Neter, J., and W. Li (2005) Applied Linear Statistical Models, 5th edition. McGraw-Hill, Boston.

See Also

cor

Examples

Y <- rnorm(100)
X <- rnorm(100)
press(lm(Y ~ X))

[Package asbio version 1.9-7 Index]