Stats PLS Test

*It was recommended to test through Andrew Hayes Process as its ‘easy’ : [login to view URL] Pilot Study The reliability and validity of the research instrument must be assessed to evaluate the measurement model in terms of item reliability, convergent validity( individual item reliability) and discriminant validity. Reliability Reliability in a survey is the stability of the measures it uses. Each survey constructs have different items which assess internal consistency. In PLS it is advisable to calculate the composite reliability where the accepted value should exceed 0.70 and should be interpreted by Cronbach’s alpha. Convergent and discriminant validity PLS should be used to test the convergent and discriminant validity of the scales. In a CFA by PLS convergent validity is proved if a measurement loads highly( with a coefficient above 0,60)or very significantly( if its T-values are within the 0.01 level of their assigned constructs. Table 4 shows the factor loadings of the measurement items and their T-values. The factor loadings need to demonstrate convergent validity and all the t-values are also above 1,96. ( note: if any of the above constructs have loadings less than the threshold 0,7 they need to be excluded form the survey Discriminant validity is shown when ( indicates the extent to which a given construct is dissimilar to other constructs) 1. Measurement items load more strongly on their assigned construct rather than on the other constructs in the CFA and 2. The square root of the average variance extracted ( AVE) of each construct is larger than its correlations with the other constructs