Evaluating Group Differences in Gender During the Formation of Relationship Quality and Loyalty in ISP Service - End User Computing Challenges and Technologies: Emerging Tools and Applications - page 248

Table 4. Chi-square difference tests for examining discriminant validity

test are, respectively, χ 2 (1, 0.05/15) = 9.14 and χ 2 (1,
0.01/15) = 10.83. Since the chi-square difference
statistics for every two constructs exceed 9.14 for
each model (see Table 4), discriminant validity is
successfully achieved.

unconstrained model is estimated, in which path
coefficients are allowed to vary across the cross-
group datasets. Next, a fully constrained model is
estimated by requiring that all path coefficients are
constrained to be equal for cross-group datasets.
The fully constrained model, thus, is based on the
notion of cross-group variance in model relation-
ships. Comparing the goodness-of-fit statistics for
the unconstrained and fully constrained models by
using a χ 2 difference test will yield evidence for
examining our hypotheses. The χ 2 statistics for the

testing for the moderating effects

This study uses the analytical strategy of Singh
(1995) to examine the existence of the moder-
ating effect on the structural model. First, an