Using a Bonferroni adjusted a priori p-value of .01 (.05/5), the population means
for the three groups are judged to be unequal on the extraversion, openness-toexperience,
and agreeableness traits. The largest univariate effect is noted for
extraversion, for which 15% (h2 = .15) of the variability in the extraversion trait
scores can be explained by group membership. This effect seems small, although
it could be judged as large using Cohen’s (1988) conventions (.01 = small, .06 =
medium, .14 = large). It should also be noted the homogeneity of population
variances assumption was tested for each analysis and no violations were noted.
Each of the statistically significant univariate, omnibus effects could be followed
by complex or paired comparisons to clarify the nature of the mean differences
between the EA, AA, and AI groups. The results from such analyses would
be interpreted separately for each of the Big Five trait scores because the univariate
approach essentially treats any potential correlations among the dependent
variables as meaningless.
By comparison a multivariate approach takes into account the inter-correlations
among the Big Five personality traits. As can be seen in the following SPSS
CORRELATION output, a number of the trait scores are modestly correlated: