#SmartPLS4

The session focuses on how to assess the predictive power of the model using PLSPredict in SmartPLS4. The sessions starts with the concept of Predictive power, the theory behind it, the process of predictive power assessment, and finally practical illustration of how to assess predictive power using PLS Predict in SmartPLS4.
Do you have any questions, tips, or ideas? Let me know in the comments section below!
About:
Research With Fawad is a Research initiative to help young and early career research learn the research tools and techniques. It is an initiative to share research knowledge and help researchers learn to research the easy way.
Learn more about Research With Fawad at www.researchwithfawad.com.
#smartpls #smartpls4 #predictivepower #predictivevalidity #plssem #sem #TrainingSmaple #HoldoutSample #OutofSamplePredictivePower

[@yvescostanetto5267]

Congratz, mate. Easy and detailed explanation.

[@researchwithfawad]

Glad you liked it!

[@seyedjafarmousavi6973]

Great toturial, thank you very much 🙏🏼💐

[@researchwithfawad]

Thanks. I am glad you liked it

[@imaaronds6914]

Thank you so much

[@researchwithfawad]

Thanks. I am glad you liked it. Please do circulate 8n your research circle.

[@farmagold2239]

Gracias información valiosa. siga por favor gracias

[@researchwithfawad]

Thanks. I ma glad you liked it

[@nourosama119]

Thank you sir for your very informative sessions! I have a question if I have a higher-order reflective-formative construct as a dependent variable that was developed using the disjoint two-stage approach, can I use PLSpredict to assess the model's predictive relevance or not? also if it is not possible. how should the structural model assessment go? just report on direct relations path coefficients and R2?

[@researchwithfawad]

Yes, you can use PLSPredict.

[@nehavarma8654]

Thank you so much sir for providing very useful information. could you please provide the reporting of predictive power in the thesis? with your videos, I was able to report all the results except the predictive power of the model. I would be very grateful if you include reporting video also.

[@researchwithfawad]

Thanks. I am glad you liked it. I am sorry but haven't made any video on it yet. However Search Google scholar with following strings to get paper that have.
allintext:"SmartPLS" "PLSPredict"

[@nehavarma8654]

@@researchwithfawad thanks alot sir for you support..!! :)

[@adeelmunir3320]

How we can use PLSPredict for higher order constructs?. Should we compare and report the RMSE values of only lower order construct or should we include higher order as well?

[@researchwithfawad]

Unfortunately, at the moment only repeated-indicators approach will work to generate predictions for PLS models. So you can use PLSpredict when estimating a repeated-indicators construct.
However, there is currently no solution for using two-stage estimation method to conduct PLS-predict.

[@xuegewang9335]

Hi professor, if one indicator has a Q2predict0 and RMSE value

[@researchwithfawad]

Yes you can.

[@qaisbatiha2309]

first and foremost I really thank you so much I learned from you more than the lecturer I paid him "May Allah accept it as your good deeds and bless".
Something else I would like to ask, is how I can report the predictive model in the thesis?

[@researchwithfawad]

Thanks. I am glad you liked it.
You can out in a para after hypotheses testing. Mention if it was high or medium based on the comparisons plus the table as provided by the Smart PLS

[@AP_Pathak]

Sir, how to report it like the explanatory power table that you made and stated the description of the table? if you can make a video on reporting the predictive power table then it will be beneficial

[@researchwithfawad]

Thanks for your interest. I hope to make one soon. For now you can search google scholar with the following string to find papers that have used PLS Predict and see how they report it.
allintext:"PLS Predict"

[@Alhamzah_F_Abbas]

Very interesting explanation. well done. can we get the content of this video, please?

[@researchwithfawad]

Thanks. I will try to upload soon on the website.

[@glowingstars8163]

There is already q saqure value in table which show the predictive power ,then why u use RMSE and MAE for predictive power .is it necessary?

[@researchwithfawad]

That is for Predictitive Relevance

[@AP_Pathak]

sir when to report model predictive power?

[@researchwithfawad]

You can report after reporting the R-Sq