![MathJax Logo](/templates/jsp/_style2/_tandf/pb2/images/math-jax.gif)
This note is to provide proofs of sufficiency for Propositions A.3 and A.5 in LaMotte (Citation2018).
1. Formulation of psn
The incidence matrix for a setting with cell sample sizes ,
is a matrix
with
rows and ab columns, where the i,j,s-th row has a 1 in the i,j column and zeroes in all the other columns. This means that the i,j-th column has
ones, and every row has exactly one 1.
Models for effects are built with matrices defined as follows. For each positive integer m, define and
. For dummy variables, define
,
,
, and
. For definitions of ANOVA effects, define
,
,
, and
.
The property ‘proportional subclass numbers’ (psn) is defined here to mean that there exist positive integers and
such that
,
. Let
and
. Then
,
, and
. Matrices defined in LaMotte (Citation2018) are
and
Let and
. Then, if
for all i,j,
can be formed by permuting the rows of
, so that there exists an
by
orthogonal matrix R such that
, or
.
Recall that
and, from (A2) in LaMotte (2018),
(1)
(1)
2. Proposition A.3
The proof of necessity is correct: that is,
,
. While it is true that
, the implication in the other direction is not true. Following is a proof of sufficiency.
Proposition A.3, sufficiency. If ,
, then
.
Proof. That ,
, means that
,
, and hence that
and
.
Note that . Then
Then
, which implies that
and hence
which, since R is orthogonal, implies that
.
3. Proposition A.5
The additive model is . Within it, the model that includes no A effects is
. Then the extra SSE due to omitting possible A effects is
. This is otherwise known as Type II SS for A effects. The argument given for Proposition A.5 proves necessity, that if
then
for all i,j. The purpose of this section is to provide a proof of sufficiency.
Proposition A.5, sufficiency. If for all i,j, then
Proof. We shall show that
and hence the result, by showing that
First note that
Then
and so
from (Equation1
(1)
(1) ). It follows that
.
Reference
- LaMotte, LR. Proportional subclass numbers in two-factor ANOVA. Stat: J Theoret Appl Stat. 2018;52:228–238. doi: 10.1080/02331888.2017.1319834