How to Validate Formative Model in SmartPLS

[@chefberrypassionateresearcher]

Sir, if some items have negative outer loadings, but their significance value is below .5, What to do with such negative items of the formative construct?

[@researchwithfawad]

Check if they are reverse items

[@Alhamzah_F_Abbas]

informative session prof. thank you so much

[@researchwithfawad]

You are welcome

[@chefberrypassionateresearcher]

Sir, how to do COMMOM METHOD BIAS TESTING AND MEASUREMENT INVARIANCE BEFORE DOING MGA IN MSART PLS? I have a single formative construct which predicts a single reflective construct.

[@researchwithfawad]

Please read about Harman Single Factor Test

[@mostafajerari7560]

Hi. Could you tell me how to solve the problem of inverted signs (positive/negative) of the outer weight (Path coefficients) in Smart PLS. Thank you

[@researchwithfawad]

Are there any reverse items, if so, you have to reverse code the items in your study.

[@mostafajerari7560]

@@researchwithfawad Thank you very much for your hopeful explanations. I'll try to see what you have recommande me and i hope it resolve the issue.

[@yllwgurl3099]

Hi Sir. Why do we see outer loading in bootstrapping not in pls algorithm?. Thanks

[@researchwithfawad]

To asses the the outer loadings along with its significance for formative indicators.

[@yllwgurl3099]

@@researchwithfawad Thank you Sir. I humbly have another question. In the vif there are 2 space. Outer vif value and inner vif value. Can we use the value from inner vif sir?, what's the different between that?. Thanks

[@researchwithfawad]

For validity use outer for structural relationships use inner.

[@yllwgurl3099]

@@researchwithfawad thank you so much Sir

[@LittleAwesomeMiracles-kw3kn]

Hi, sir May i know how to treat collinearity issues as the VIF is bigger than 5. Should i just remove the indicators or should i consider another way?

[@researchwithfawad]

You may try multi-group analysis to see which group have high VIF values. Plus make sure you clean the data before running the analysis.

[@chefberrypassionateresearcher]

Dear professor, I have a doubt. Why didnt you check validity using single global measurement item (Redundancy analysis). There is no overall/ global measurement item in your model. Please clarify..

[@researchwithfawad]

Since I didn't collect data on it. I only focused on the other statistics

[@Sanjida_Hassan]

Sir, is it necessary to do the Redundancy Analysis for validating formative measurement items?

[@hamzabuzdar2422]

Sir can we use smart pls to test a theory ? As in literature it is mentioned that one should for amos , but in IF papers I have seen pls has been used for to test a theory.

[@researchwithfawad]

Yes you can use it to test a theory.

[@ungkunorani7735]

Salam Dr. Fawad, thank you for a very helpful video. Do you have a video tutorial on convergent validity for formative measurement model?

[@researchwithfawad]

I don't have any yet but according to Prof. Ringle the best option is using a reflective measurement model of the same model. But usually you do not have indicators for both types of measurment models. The second best option - as a workaround and good approximation - is using the single indicator that represents the scale. If you don't have this one, the third best option is using a very similar construct that you have in the measurment model.

[@ungkunorani7735]

​@@researchwithfawad Thank you very much Dr. Fawad. I humbly have another question. Once I run the algorithm on my formative model, if there is any negative value on the indicators shown on my path model, should I immediately delete the indicator?

[@researchwithfawad]

Negative value? Where on the outer weights or paths?

[@ungkunorani7735]

@@researchwithfawad on path model Dr. but outer loading is greater than 0.50

[@researchwithfawad]

Negative value on path means a negative relationship between the variables. Send me the screenshot on [e-mail]

[@graciamariaandino6274]

can you permit tha traduction option please? I need the subtitles in Spanish.

[@researchwithfawad]

Thanks for the interest. Actually I have allowed it. But i will further look into it.

[@hamzabuzdar2422]

I have seen you videos , Sir I have a question and I hope you will answer it when you have free time. Sir my question is that I have DV ( sustainable performance) and in literature it is a multidimensional construct based on three dimensions that are economic performance, environmental performance and social performance, now its conceptual definition is also based on three dimensions now sir can operationalise this construct based on two dimensions that is environmental performance and social performance and can skip the economic performance.? Reason: sir actually my target organisation are public sector hospitals and mostly they are non profit organisations and there is no economic performance (growth profit, market share etc) in these organisations. Secondly can I run analysis on pls? In this situation or should go for Amos. ? Or can do efa separately and then run pls ? JazakAllah

[@researchwithfawad]

Hamza, you have a reason to skip the economic dimension of SP.

[@hamzabuzdar2422]

Thankyou very much sir

[@asadkhan-bz4op]

Dropped you an email, looking forward to your reply

[@researchwithfawad]

Please check your email