Dear PLS-experts,
My model consists of three 2nd order formative-formative constructs and two 2nd order reflective-formative constructs (among others).
Now, I would like to ckeck for unobserved heterogeneity by means of PLS-POS.
I'm just wondering how to do this in an appropriate way as I could not find any literature on this special case.
I would be very grateful if someone could give me an advice how to deal with this issue properly.
Many thanks in advance.
Best regards
Martha
2nd order constructs and PLS-POS
- Hengkov
- PLS Super-Expert
- Posts: 1599
- Joined: Sun Apr 24, 2011 10:13 am
- Real name and title: Hengky Latan
- Location: AMQ, Indonesia
- Contact:
Re: 2nd order constructs and PLS-POS
Hi,
Check this reference
Becker, J.-M., Rai, A., Ringle, C. M., & Völckner, F. (2013). Discovering unobserved heterogeneity in structural equation models to avert validity threats. MIS Quarterly, 37(3), 665-694.
I always say that approach to test unobserved heterogeneity (FIMIX, PLS-POS, PATHMOX, PLS-GAS, etc) will always generate segement or same group as cluster analysis. So researchers had to make a strong reason to test this.
Best regards,
Check this reference
Becker, J.-M., Rai, A., Ringle, C. M., & Völckner, F. (2013). Discovering unobserved heterogeneity in structural equation models to avert validity threats. MIS Quarterly, 37(3), 665-694.
I always say that approach to test unobserved heterogeneity (FIMIX, PLS-POS, PATHMOX, PLS-GAS, etc) will always generate segement or same group as cluster analysis. So researchers had to make a strong reason to test this.
Best regards,
Last edited by Hengkov on Mon Aug 10, 2015 9:34 am, edited 1 time in total.
-
- PLS Junior User
- Posts: 2
- Joined: Fri Aug 07, 2015 7:59 am
- Real name and title: Martha Werner
Re: 2nd order constructs and PLS-POS
Dear Hengkov,
Many thanks for your quick reply. I really appreciate it.
Thank you for literature recommendation. I already read the article.
The reason why I would like to check for unobserved heterogeneity is that it seems to be a "must" in the overall evaluation process (according to literature) and I want to check if my overall sample is actually homogenous.
And if I understood you and the literature correctly there is nothing special to take care of when dealing with 2n order constructs. Again, many thanks for your advice.
Best regards
Martha
Many thanks for your quick reply. I really appreciate it.
Thank you for literature recommendation. I already read the article.
The reason why I would like to check for unobserved heterogeneity is that it seems to be a "must" in the overall evaluation process (according to literature) and I want to check if my overall sample is actually homogenous.
And if I understood you and the literature correctly there is nothing special to take care of when dealing with 2n order constructs. Again, many thanks for your advice.
Best regards
Martha