General

In SmartPLS, results are highlighted depending on whether a certain threshold is reached for a particular analysis. These thresholds are mainly based on the recommendations of

• Hair, J. F., Hult, G. T. M., Ringle, C. M., & Sarstedt, M. (2022). A primer on partial least squares structural equation modeling (PLS-SEM), 3rd ed., Thousand Oaks, CA: Sage.

• Hair, J. F., Sarstedt, M., Ringle, C. M., & Gudergan, S. P. (2024). Advanced issues in partial least squares structural equation modeling (PLS-SEM), 2nd ed., Thousand Oaks, CA: Sage.

The following graph shows PLS-SEM results for construct reliability and validity. Cronbach's alpa, composite reliability (rho_a), and composite reliability (rho_c) appear in green font if their value is at and above 0.7, otherwise the font color is red. For the average variance extracted (AVE), the threshold is 0.5 (above this value and above, the color is green, below it red).

Below we give an overview of different thresholds.

PLS-SEM algorithm results report including consistent PLS (PLSc)

--> Final results --> Outer loadings: green if >= 0.7 and red if < 0.7

--> Quality criteria --> f-square: green if >= 0.15 (moderate), black if >= 0.02 (small), and red if < 0.02 (negligible)

--> Quality criteria --> Construct reliability and validity --> Cronbach's alpha: green if >= 0.7 and red if < 0.7

--> Quality criteria --> Construct reliability and validity --> composite reliability rho_a: green if >= 0.7 and red if < 0.7

--> Quality criteria --> Construct reliability and validity --> composite reliability rho_c: green if >= 0.7 and red if < 0.7

--> Quality criteria --> Construct reliability and validity --> average variance extracted (AVE): green if >= 0.5 and red if < 0.5

--> Quality criteria --> Discriminant validity --> heterotrait-monotrait ratio (HTMT): green if <= 0.85, black if <= 0.9, and red > 0.9

--> Quality criteria --> Discriminant validity --> Variance inflation factor (VIF): green if <= 3, black if <= 5, and red if > 5

Bootstrapping including PLS (PLSc) bootstrapping, bootstrap multigroup analysis (MGA), and PLSc bootstrap MGA

In the start dialog of the bootstrapping procedure, the significance level is set (e.g., 0.05). All bootstrap p values less than or equal to this value appear in green in the bootstrapping result report, p values above this value appear in red.

PLSpredict

--> Final results --> MV prediction summary --> Overview --> Q²: green if >= 0 and red if <0

--> Final results --> MV prediction summary --> Overview --> PLS-SEM_RMSE: green if PLS-SEM_RMSE < LM_RMSE, otherwise red

--> Final results --> MV prediction summary --> Overview --> PLS-SEM_MAE: green if PLS-SEM_MAE < LM_MAE, otherwise red

Permutation multigroup analysis (MGA) including consistent PLS (PLSc) permutation MGA, and measurement invariance of composite models (MICOM)

In the start dialog of the permutation procedure, the significance level is set (e.g., 0.05). All permutation p values less than or equal to this value appear in green in the bootstrapping result report, p values above this value appear in red.

--> Quality criteria --> MICOM --> Step 2 Based on the specified significance level, values equal to or above this level (e.g. 0.05) appear in green, otherwise in red. Note: in this case, larger p values allow to reject the null hypothesis that the correlation of a composite's group-specific computation is unequal 1.

--> Quality criteria --> MICOM --> Step 3a and 3b

Based on the specified significance level, values less than or equal to this level (e.g. 0.05) appear in green, otherwise in red.