How to Solve Convergent and Discriminant Validity Issues
Addressing Convergent and Discriminant Validity Issues
How to Solve Convergent and Discriminant Validity Issues? Learn to Solve the common issues faced in establishing convergent and discriminant validity. The tutorial along with the video will guide the researcher to solve the problems related to establishing convergent and discriminant validity.
Before Collection the Data
- Make sure to have adequate No. of Items in each scale/construct.
- There should be at least 4-6 items, since, in SEM items are deleted if they fail to load or due to cross-loading.
- Make sure that the Items/Statements are easy to understand.
- Make sure there is no overlap in the statements of different constructs.
Recommendation to Solve Convergent and Discriminant Validity Issues
- Check for item factor loading, if item loading is too low and removing the items can substantially improve the convergent validity, remove the item.
- If discriminant validity issues persist, no option may exist but to combine constructs into one overall measure, where correlations in the region of 0.8 to 0.9 are regularly reported in the literature between dimensions that are
theoretically distinct. In such cases, researchers can collapse measures into a single construct, rather than conduct dimension-by-dimension analysis. - If none of the methods presented address the issue, a researcher may have to collect additional data to determine if discriminant validity or multicollinearity issues are a result of sampling flukes.
- If problems still persist, dropping one (or more) independent variables (i.e., collinear variables that demonstrate insufficient discriminant validity) from the model may also help.
- Check for Cross-loading, if an item is cross-loading, and the difference is less than .10, REMOVE the item(s).