Robust F-Test: Wald test for multiple coefficients of rlm() Object

Compute a robust F-Test, i.e., a Wald test for multiple coefficients of an rlm object.

Usage

f.robftest(object, var = -1)

Arguments

object

result of rlm().

var

variables. Either their names or their indices; the default, -1 means all but the intercept.

Details

This builds heavily on summary.rlm(), the summary method for rlm results.

Value

An object of class "htest", hence with the standard print methods for hypothesis tests. This is basically a list with components

statistic

the F statistic, according to ...

df

numerator and denominator degrees of freedom.

data.name

(extracted from input object.)

alternative

"two.sided", always.

p.value

the P-value, using an F-test on statistic and df[1:2].

References

FIXME — Need some here !

Author

Werner Stahel, July 2000; updates by Martin Maechler.

See also

rlm, summary.aov, etc.

Examples

if(require("MASS")) {
  ## same data as  example(rlm)
  data(stackloss)
  summary(rsl <- rlm(stack.loss ~ ., stackloss))
  f.robftest(rsl)
 } else  " forget it "
#> Loading required package: MASS
#> 
#> 	robust F-test (as if non-random weights)
#> 
#> data:  from rlm(formula = stack.loss ~ ., data = stackloss)
#> F = 90.189, p-value = 1.212e-10
#> alternative hypothesis: two.sided
#> null values:
#>   Air.Flow Water.Temp Acid.Conc. 
#>          0          0          0 
#>