R help - Nov 2009 - KhmaladzeTest in quantreg

Hi,
I've implemented the KhmaladzeTest for my linear quantile regression model
for the location-scale shift hypotesis as follow:
>formula=r ~ div + pe + por
>Ktest=KhmaladzeTest(formula,nullH="location-scale")
> Ktest
$nullH
[1] "location-scale"

$Tn
[1] 2.125804

$THn
div                     pe       por 
 0.7972984  1.4432325  0.7107914 

attr(,"class")


Now I have to compare the number 2.125804 with the critical values that I found
in Koenker and Xiao (2002) which are:
 - 1% critical value 5.350
 - 5% critical value 4.523

So I accept the null.

But if I carry out the test for the location shift hypotesis 

the result is:

$Tn
[1] 3.178942

and I accept the null again! How is it possible??? Is there something wrong in
my estimation?

Thank you for your help!

Antonella Cannito

 
	[[alternative HTML version deleted]]