Re: [Gretl-users] GUI points
Am 12.11.2016 um 23:12 schrieb Allin Cottrell:
Hmm, I guess so. Maybe worth noting that Belsley's condition
number
calculation involves scaling but not centering. So try the following:
<hansl>
open hall.gdt
series c10 = consrat * 10
series cc = consrat - mean(consrat)
eval cnumber({const, ewr, consrat})
eval cnumber({const, ewr, c10})
eval cnumber({const, ewr, cc})
</hansl>
Multiplying consrat by 10 makes no difference to the condition number,
as you say. But centering it reduces the value a great deal. (With
correlation, of course, neither scaling not centering makes any
difference.)
(And centering ewr, too, then leads to cnumber values below 2, BTW.)
I haven't looked (or wasn't forced to look) at these concepts in the
past, but this behavior of the condition number I find odd. It feels as
if it makes only sense if the data are demeaned. And including a
constant term in the variable set for the calculation of cnumber
obviously doesn't do the same thing.
thanks,
sven