How to compare formative and relfctive measurement model?

[NewVincent]

Dear all,

I'm new to PLS, in this case what shall I do?

I'm trying to prove that 2nd order formative measurement model of perceived value is better than reflective measurement model.

That's:
reflective measurement model: indicator <- 1st order <- 2nd order
formative measurement model: indicator <- 1st order -> 2nd order

I run these two models in SmartPls, but I'm confused with the resulets.

Through which Index or test, I can conclude which model's better?
Is there anything like RMSEA in Lisrel?

Thank you very much in advance.

XiaoBo Gong

[mengchuanjin]

Dear all,

I'm new to PLS, in this case what shall I do?

I'm trying to prove that 2nd order formative measurement model of perceived value is better than reflective measurement model.

That's:
reflective measurement model: indicator <- 1st order <- 2nd order
formative measurement model: indicator <- 1st order -> 2nd order

I run these two models in SmartPls, but I'm confused with the resulets.

Through which Index or test, I can conclude which model's better?
Is there anything like RMSEA in Lisrel?

Thank you very much in advance.

XiaoBo Gong

you can't do this.

[schroer]

Hello,

there's no way to directly do this in SmartPLS (apart from looking at the diverse quality indicators like AVE etc., of course).

Instead, you might want to have a look at the "vanishing tetrads" method suggested by Bollen and Ting, which does not involve PLS at all though:

Bollen, K. A., & Ting, K.-f. (2000). A tetrad test for causal indicators. Psychological Methods, 5, 3-22.

Apart from that, it comes down to theoretical reasoning, I guess... ;-)

Best wishes,

Joachim