total of the summation of standardized loading square and the sum of indicator
measurement error (Hair et al 1998).
For discriminant validity, the measures of theoretically different constructs
should not correlate highly with each other. In other words, the items should load more
strongly on their own construct (Byrne 1994, Byrne and Goffin 1993). Cross-construct
correlations should be low in-order to show the evidence of discriminant validity.
According to Fomell and Larcker (1981) discriminant validity is shown when the
shared variance (squared correlation) between any two constructs is less than the average
variance extracted by the items measuring the construct. Table 4.7 shows the evidence of
discriminant validity