Multiple ANOVA

CJ Queano
Gem Pedro
Richmond Tiopengco

The use of ANOVA to study the effects of multiple

factors has a complication. In a 3-way ANOVA with

factors x, y and z, the ANOVA model includes terms for
the main effects (x, y, z) and terms forinteractions(xy,
xz, yz, xyz). All terms require hypothesis tests. The
proliferation of interaction terms increases the risk that
some hypothesis test will produce a false positive by
chance. Fortunately, experience says that high order
interactions are rare.The ability to detect interactions
is a major advantage of multiple factor ANOVA. Testing
one factor at a time hides interactions, but produces
apparently inconsistent experimental results

A variety of techniques are used with multiple

factor ANOVA to reduce expense. One

technique used in factorial designs is to
minimize replication (possibly no replication
with support ofanalytical trickery) and to
combine groups when effects are found to be
statistically (or practically) insignificant. An
experiment with many insignificant factors
may collapse into one with a few factors
supported by many replications.

Difference
The one-way analysis of variance (ANOVA) is

used to determine whether there are any

significant differences between the means of
two or more independent (unrelated) groups
(although you tend to only see it used when
there are a minimum of three, rather than two
groups).

With two-factor analysis of variance, there are

two study factors (we'll call them factor A

withalevels and factor B withblevels) and we
study all (atimesb) combinations of levels.
The secret to mastering two-factor analysis of
variance is to understand the underlying model.
The principal reason why multi-factor analysis
are interpreted incorrectly is that users do not
understand what is meant by the seductively
namedmain effect. Amain effectis the effect
of a particular factoron average.

In a multi-factor analysis of variance, we look

atinteractionsalong with main effects.

Interactions are the extent to which the effects of
one factor differs according to the levels of another
factor. If there is an interaction between DRUG and
SEX, say, the drug that is best for men might be
different from the one that is best for women. If
there is no interaction between the factors, then
the effect of one factor is the same for all levels of
the other factor. With no interaction, the drug that
is best on average is the best for everyone.

Assumptions
1. Yourdependent variableshould be measured at
2.
3.

4.
5.

6.

thecontinuouslevel
Yourtwo independent variablesshould each consist
oftwo or more categorical,independent groups.
You should haveindependence of observations, which
means that there is no relationship between the observations
in each group or between the groups themselves.
There should beno significant outliers.
Yourdependent variableshould beapproximately
normally distributed for each combination of the
groups of the two independent variables.
There needs to behomogeneity of variances for each
combination of the groups of the two independent
variables.

 With only a slight exaggeration, if you

understand two-factor analysis of variance,

you understand all of multi-factor analysis of
variance. If you understand the issues raised
by analyzing two factors simultaneously, then
you'll understand the issues regardless of the
number of factors involved.