partial.R2: Partial correlations of determination in multiple regression

In asbio: A Collection of Statistical Tools for Biologists

Partial correlations of determination in multiple regression

Description

Calculates the partial correlation of determination for a variable of interest in a multiple regression.

Usage

partial.R2(nested.lm, ref.lm)

Arguments

nested.lm	A linear model without the variable of interest.
ref.lm	A linear model with the variable of interest.

Details

Coefficients of partial determination measure the proportional reduction in sums of squares after a variable of interest, X, is introduced into a model. We can see how this would be of interest in a multiple regression.

Value

The partial R^2 is returned.

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, partial.resid.plot

Examples

Soil.C<-c(13,20,10,11,2,25,30,25,23)
Soil.N<-c(1.2,2,1.5,1,0.3,2,3,2.7,2.5)
Slope<-c(15,14,16,12,10,18,25,24,20)
Aspect<-c(45,120,100,56,5,20,5,15,15)
Y<-as.vector(c(20,30,10,15,5,45,60,55,45))

lm.with<-lm(Y~Soil.C+Soil.N+Slope+Aspect)
lm.without<-update(lm.with, ~. - Soil.N)

partial.R2(lm.without,lm.with)

asbio documentation built on May 29, 2024, 5:57 a.m.