Microsoft Word 2007 ichrie conference Proceedings Final-Final 06-06-07. doc

Multivariate Analysis of Variance (MANOVA) 
Structural equation modeling showed correlation among the seven extracted factors. Multivariate Analysis 
of Variance (MANOVA) was performed to examine the gender, group, and gender by group effects on the 
dependent variables represented by the seven factors. Before conducting MANOVA, multiple regressions were 
conducted to obtain the Mahalanobis distance (p < .001) to check for outliers and screen for multicollinearity among 
the seven dependent variables, no evidence of multicollinearity among the variables and no outliers were identified. 
The results showed that there were significant differences due to gender (Wilks’ Lambda= .873, F (7,214) = 4.444, 
p<.01) and group (Wilks’ Lambda= .765, F (14,428) = 4.390, p<.01). No significant gender by group interaction 
was found. Table 1 shows MANOVA results. Univariate ANOVAs were performed for each dependent variable 
(Hummel & Sligo, 1971); independent variables were gender and group. Table 2 shows the ANOVA results.
 
Table 1