Validation
Under the measurement model, two types of validity are relevant-
convergent validity and discriminant validity. It refers to the extent
to which multiple items measure the same concept are in agreement. As
posited by Hair et al. (2010), factor loadings, composite reliability
and average variance were used in assessing convergence validity. The
standard measures for these elements are Loadings (> 0.7),
CR (> 0.7) and AVE (> 0.5). If the measures
are above the cut-off values, then the measures are said to have
adequate convergent validity.
Discriminant validity, on the other hand, is the degree to which items
differentiated among the study construct or measure distinct concepts/
variables by examining the correlations between the measures of a
possible overlapping construct. Items should load strongly in their
construct in the model, and the mean variance shared between each
construct, and its measure should be greater than the variance shared
between the construct and other constructs (Fornell & Larcker, 1981,
Campeau et al., 1999)