In SmartPLS, what are the most appropriate criteria to evaluate the goodness of fit for a model with both reflective and formative constructs, and how can you address issues related to the reliability and validity of the measures used?
When using SmartPLS to evaluate a model with both reflective and formative constructs, there are several criteria that can be used to evaluate the goodness of fit of the model. These include:
R-squared (R²): R-squared measures the proportion of variance in the dependent variable(s) that is explained by the independent variable(s). For reflective constructs, R² values above 0.1 are considered acceptable, while for formative constructs, R² values above 0.25 are considered acceptable.
Goodness-of-fit index (GoF): GoF is a measure of the overall fit of the model, taking into account the number of variables and indicators in the model. A GoF value of 0.36 or higher is considered acceptable.
Average Variance Extracted (AVE): AVE measures the amount of variance that is captured by the construct's indicators. For reflective constructs, AVE values above 0.5 are considered acceptable, while for formative constructs, AVE values above 0.7 are considered acceptable.
Composite Reliability (CR): CR measures the internal consistency or reliability of the construct's indicators. CR values above 0.7 are considered acceptable.
To address issues related to the reliability and validity of the measures used, several steps can be taken. These include:
Conducting a pilot test: Before collecting data, a pilot test can be conducted to test the validity and reliability of the measures.
Using established measures: Whenever possible, established measures with proven reliability and validity should be used.
Conducting a reliability analysis: Before running the model, a reliability analysis can be conducted to test the internal consistency of the measures.
Conducting a validity analysis: After running the model, a validity analysis can be conducted to test the construct validity of the measures.
Using multiple methods: To improve the validity of the measures, multiple methods (such as surveys, interviews, and observational measures) can be used to collect data.