Dear all,
I am exploring a formative (formative-formative-formative) third-order model.
For purposes of model identification, I need to ensure the formative construct has at least two structural paths to reflective constructs?
Should I use two-stage approach or repeated indicator approach?
I will appreciate your comments.
Regards,
Mariana
Formative Model Identification
-
- PLS Junior User
- Posts: 6
- Joined: Mon Feb 29, 2016 11:11 am
- Real name and title: Mariana Martins Rodrigues
-
- PLS User
- Posts: 16
- Joined: Thu Oct 17, 2013 10:04 am
- Real name and title: Marc Janka
- Location: Germany
Re: Formative Model Identification
Dear Ms. Rodrigues
A construct in PLS is identified irrespectively whether it is estimated using mode A or B when there is at least one more endogenous or exogenous latent variable, i.e., the 'two or more dependents' identification rule won't be necessary (see Becker et al. 2013). However, I would recommend using at least one 'overall' indicator as 'phantom' or 'ghost' variable in order to establish nomological validity and to ensure content validity of your formative construct when using mode B for endogenous constructs (see Götz et al., 2010; Hair et al., 2014). Both approaches, repeated indicator and two stage approach, perform well depending on your underlying research question, e.g., model complexity and so on (Becker et al., 2012). Particularly, when you aim to estimate an endogenous second order formative model you have to apply the two stage approach to get 'valid' estimations for your path coefficients and R² (Ringle et al., 2012).
Best
MJ
Götz, O., Liehr-Gobbers, K., & Krafft, M. (2010). Evaluation of structural equation models using the partial least squares (PLS) approach. In V. Esposito Vinzi, W. W. Chin, J. Henseler & H. Wang (Eds.), Handbook of partial least squares (pp. 691–711): Springer.
Ringle, C. M., Sarstedt, M., & Straub, D. W. (2012). A critical look at the use of PLS-SEM in MIS Quarterly. MIS Quarterly, 36(1), iii–xiv.
Becker, J.-M., Klein, K., & Wetzels, M. (2012). Hierarchical Latent Variable Models in PLS-SEM: Guidelines for Using Reflective-Formative Type Models. Long Range Planning, 45(5–6), 359–394.
Becker, J.-M., Rai, A., & Rigdon, E. E. (2013). Predictive Validity and Formative Measurement in Structural Equation Modeling: Embracing Practical Relevance. Paper presented at the Thirty Fourth International Conference on Information Systems, Milan.
Hair, J. F., Hult, G. T. M., Ringle, C. M., & Sarstedt, M. (2014). A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM). Thousand Oaks: Sage.
A construct in PLS is identified irrespectively whether it is estimated using mode A or B when there is at least one more endogenous or exogenous latent variable, i.e., the 'two or more dependents' identification rule won't be necessary (see Becker et al. 2013). However, I would recommend using at least one 'overall' indicator as 'phantom' or 'ghost' variable in order to establish nomological validity and to ensure content validity of your formative construct when using mode B for endogenous constructs (see Götz et al., 2010; Hair et al., 2014). Both approaches, repeated indicator and two stage approach, perform well depending on your underlying research question, e.g., model complexity and so on (Becker et al., 2012). Particularly, when you aim to estimate an endogenous second order formative model you have to apply the two stage approach to get 'valid' estimations for your path coefficients and R² (Ringle et al., 2012).
Best
MJ
Götz, O., Liehr-Gobbers, K., & Krafft, M. (2010). Evaluation of structural equation models using the partial least squares (PLS) approach. In V. Esposito Vinzi, W. W. Chin, J. Henseler & H. Wang (Eds.), Handbook of partial least squares (pp. 691–711): Springer.
Ringle, C. M., Sarstedt, M., & Straub, D. W. (2012). A critical look at the use of PLS-SEM in MIS Quarterly. MIS Quarterly, 36(1), iii–xiv.
Becker, J.-M., Klein, K., & Wetzels, M. (2012). Hierarchical Latent Variable Models in PLS-SEM: Guidelines for Using Reflective-Formative Type Models. Long Range Planning, 45(5–6), 359–394.
Becker, J.-M., Rai, A., & Rigdon, E. E. (2013). Predictive Validity and Formative Measurement in Structural Equation Modeling: Embracing Practical Relevance. Paper presented at the Thirty Fourth International Conference on Information Systems, Milan.
Hair, J. F., Hult, G. T. M., Ringle, C. M., & Sarstedt, M. (2014). A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM). Thousand Oaks: Sage.
-
- PLS Junior User
- Posts: 6
- Joined: Mon Feb 29, 2016 11:11 am
- Real name and title: Mariana Martins Rodrigues
Re: Formative Model Identification
Once again, thank you for your precious help.
-
- PLS Junior User
- Posts: 3
- Joined: Sat Apr 30, 2016 10:53 pm
- Real name and title: Araceli Rojo Gallego-Burín, PhD
Re: Formative Model Identification
Hello
I have read the references provided but I dont undestand the second step of the two step approach. Could you help me with this?
Thank you in advance.
Araceli
I have read the references provided but I dont undestand the second step of the two step approach. Could you help me with this?
Thank you in advance.
Araceli