Date: Dec 5, 2012 8:25 AM
Author: Halitsky
Subject: “L-H Het” Table for Average Slopes Auq, Aubu, Au<br> bqu
Below is the ?L-H Het? table for the average slopes:

Auq (average slope of u coefficient of

regression c on (u,u^2)

Aubu (average slope of u coefficient of

regression c on (u,e,u*e)

Aubqu (average slope of u coefficient of

regression c on (e,u,u*e,u^2)

Note that ?L-H Het? is a stronger condition than ?Het? in the

previously posted table for Aube and Aubqe: in particular, for a fold

to be ?L-H Het?, its C value must be L and its S value must be H.

So again, speaking from relative ignorance here, what we need to know

to evaluate the signficance of the following table is the probability

of L-H Het = 6 and the probability of L-H Het = 4. Also, I think

there?s a more ?diffuse? probability that has to be calculated, namely

that L-H Het < 3 for every R row. But you?ll have to decide whether

this ?diffuse? probability might be significant.

Table:

a1 a3 b1 b47 c1 c2 "L-H

C S C S c S c S C S C S Het"

N1 Auq L H L H L H L H L H L H 6

Aubu L H L H H H L H L H H H 2

Aubqu L H H L H H L L L H L H 3

N2 Auq L H H H L H H H L H L H 4

Aubu H H L H L H H H L H L H 4

Aubqu H H H L L H H H L H L H 3

N3 Auq L H H H H H L H L H L H 4

Aubu L H H H L L L H L H L H 4

Aubqu L H H H H H L H L H L H 4

R1 Auq H H L H H L H H H H H H 1

Aubu H H L H L H H H H H L L 2

Aubqu H H L H H L H H H H L L 1

R2 Auq H L H H L H H L L H L L 2

Aubu H H H H H L L L L H L L 1

Aubqu H L H H L H L L H H L L 1

R3 Auq L H H H H L L L L H L H 3

Aubu L H H H H L L L L H H L 2

Aubqu L H H H H L L L L H H L 2