[R] Collineariy Diagnostics

[Sundar Dorai-Raj]

Antoine de Bary wrote:
> Hi, and thanks for your help
> 
> in order to do collinearity analysis I downloaded the perturb package. I run
> a lm (regression) and on that the ³calldiag² commad to get condition numbers
> but i get the following message: the variable XY with modus ³numeric² was
> not found (it does the same with all predictors despite all variables are
> numeric and exists).
> 
> Can anyone tell me how can I go arround this problem? Is there another way
> to have ³condition numbers²? What about VIF?
> 
> Please return message to: antoine at ruetter.ch

I cannot comment on the "perturb" package. However for condition numbers 
see ?kappa.lm, and for variance inflation factors see ?vif. The latter 
is in the Design package.

set.seed(1)
x1 <- rnorm(100)
x2 <- x1 + 0.1 * rnorm(100)
y  <- rnorm(100)
f  <- lm(y ~ x1 + x2)

vif(f)
kappa(f)

HTH,

--sundar