Reporting Measurement and Structural Model

Measurement Model includes assessment of Quality of the Constructs including Reliability and Validity. In this session, the focus is on how to report the reliability and validity of the constructs in the study. Where reporting measurement model the scholar(s) shall start with an assessment of the Factor Loading.

Factor Loading

Factor loading show how well an item represents the underlying construct. Normally, factor loading over .70 is recommended (Vinzi, Chin, Henseler, & Wang, 2010), researchers frequently obtain weaker outer loadings (<0.70) in social science studies. However, one should not delete an item if the loading is less than.70. Instead, the scholar(s) should assess if deleting an item would significantly improve the Composite Reliability and Average Variance Extracted (AVE).

Apart from Factor Loading, measurement model shall report the Reliability (Cronbach’s Alpha and Composite Reliability) and Validity (Convergent and Discriminant Validity). Reviewers may also require other statistics to be reported like SRMR or R-Square.

Structural Model focuses on assessing the inter-relationship between the variables. The inter-relationship may only have an IV and DV (Direct Relationship), mediation analysis with a mediator in the linkage between two variables, or moderation analysis with a third variables strengthening or weakening the existing relationship between two variables.

References

Vinzi, V. E., Chin, W. W., Henseler, J., & Wang, H. (2010). Handbook of partial least squares: Concepts. Springer Science & Business Media: Methods and Applications.

In order to further Learn in Detail how to Report Measurement and Structural Model, please watch the videos