Higher-order components

Frequently asked questions about PLS path modeling.
Post Reply
yadgarhamakhan
PLS Junior User
Posts: 4
Joined: Tue Jan 29, 2019 10:49 pm
Real name and title: Yadgar

Higher-order components

Post by yadgarhamakhan »

Dear Prof

I hope you are doing well.


Kindly, I would like to ask you about this article:

https://www.sciencedirect.com/science/a ... 3?via=ihub

1-I saw in your article that you calculated the Reliability and validity manually for the second-order variable (REPU) in Table 3. Please


A-Why didn’t you get from the software? What are those numbers that the software (SmartPLS) gives us? Particularly, for the (REPU) which is 0.601, but you found 0.832 for the AVE, and so on? If 0.601 is not an AVE, then why it is in the list of AVE? I am lost and confuse between the software, and your article. Please

B-Should I also calculate it manually? Please

C-What if I do not present the reliability and validity for the second Order (REPU)? Please


2-In Table 7, you suggested that for “extended repeated indicators approach: Interpret the total effects of the antecedent constructs on the 'higher-order components'. But as I understand, you just presented Path coefficients in Table A2. Please

A-What is different between Path Coefficients results and Total Effects, If we do not need to interpret the lower order component as you mentioned “(Do not consider the lower-order components as elements of the structural model )”? As I understood, the results are the same numbers. Please

3- Will you fix this issue in SmartPLS 4?

Thank you very much for your help and your time.



I look forward to hearing from you.

Best Regards

YADGAR
Yadgar Khan
jmbecker
SmartPLS Developer
Posts: 1129
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Higher-order components

Post by jmbecker »

1.A If you carefully read the article you will understand why and when you have to calculate the numbers yourself.
You always have to do it, when you use the repeated indicator approach, because the repeated indicators are not the actual measurement of a higher-order construct that you want to evaluate. You want to evaluate the relationship to the lower-order constructs. The software cannot notice the difference, hence it cannot report the correct AVE that you want to assess.
1.B If you have a repeated-indicator model: Yes!
1.C. I don't understand the question.

2. If you carefully look at Table A2 you will find in the description below that values marked with an asterisk "*" are total effects.

3. No. There is nothing to fix. It need user intelligence to disentangle the interpretation of results.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
yadgarhamakhan
PLS Junior User
Posts: 4
Joined: Tue Jan 29, 2019 10:49 pm
Real name and title: Yadgar

Re: Higher-order components

Post by yadgarhamakhan »

Dear Prof

I hope you are doing well.

Thank you very much for your help and your time.



I look forward to hearing from you.

Best Regards

YADGAR
Yadgar Khan
Post Reply