forum.smartpls.com

Hi,

somebody told me that I couldn't measure the dependent variable in a formative manner. Is that true?

My dependent variable is "App Usage Diversity" and is measured taking into account all of the the existing app categories in the most prominent app stores. It's a formative construct and at the same time my dependent variable. If it is not possible in PLS to have a formative construct as dependent variable, what can I do?

Thanks for your answers.

Hey Kristina,

I found this topic in another post (see below) but I am not aware of the State of Art now.

I would be interested in new insights within this topic as well.

Greets

Moritz

--------------------------------------------------------------------------------
Using formatively measured endogenous latent variables is not an issue in PLS. However, from a conceptual standpoint, this type of approach is not without problems (cite from Diamantopoulos/Riefler/Roth: "Advancing Formative Measurement Models," JBR 2008:

"Concerning future research, one major issue concerns the conceptual plausibility of formatively-measured constructs occupying endogenous positions in structural models. While a number of studies incorporate formative latent variables in such positions (e.g., Edwards, 2001; Jarvis et al., 2003; MacKenzie et al., 2005), Wiley (2005, p. 124, emphasis in original) notes that there is “no mechanism by which an antecedent variable can influence a formative index”. Since the set of causal indicators and the disturbance term jointly account for the total variation of a formatively-measured construct, the specification of an additional source of variation (i.e., an antecedent con- struct) is conceptually questionable. Given the conceptual and practical importance of this issue, a debate on the use of formatively-measured constructs as endogenous variables is urgently required."
Best
Marko
--------------------------------------------------------------------------------

Hello,

I would not do this on conceptual grounds.

This area is just starting to be explored and their will be clearer guidance in the future.

Is there any way to justify your dependent as reflective?

Brad.

Actually, I don't see any problem with a formative construct as dependent variable. In fact, claiming to avaoid formative constructs in endogenous positions would be like claiming to avoid endogenous variables in PLS altogether.