## measurement model

### measurement model

hi

i know that we have 2 model, measurement and structual.

in pls graph we can run CFA easily only we nead to dont draw any connection between constructs. but how i can do it in smartpls??

when i connect all constructs with together for example i have 2 constructs , i connected construct a to construct b.

and path weighting schema

but results of factor loading have many defferences with result of factor loading in pls graph.

what i have to do?

best regards

i know that we have 2 model, measurement and structual.

in pls graph we can run CFA easily only we nead to dont draw any connection between constructs. but how i can do it in smartpls??

when i connect all constructs with together for example i have 2 constructs , i connected construct a to construct b.

and path weighting schema

but results of factor loading have many defferences with result of factor loading in pls graph.

what i have to do?

best regards

i did this work before i said wrongly path schema, i used factor schema but result have many defirrence

can u guide me? if we have 3 constructs in structual model that a is connect to b and b to c.

now if i use factor schema or path schema result is same.

1)can u say me that in this example how i can draw measurement model?

2)in application pls post i found one opinion to use one construct as both x and y but one with formative indicators and one with reflective,when i use this manner result are equal to pls graph but each time i must draw only one construct,is this true?

best regards

- Diogenes
- PLS Super-Expert
**Posts:**905**Joined:**Sat Oct 15, 2005 5:13 pm**Real name and title:****Location:**São Paulo - BRAZIL-
**Contact:**

Hi,

In PLSGraph one LV alone is estimated as if was connected with other LV with the same indicators (try with just one LV in PLSGraph and run the same in the SmartPLS, using two LVs with the same indicators = the correlations between LVs will be 1.0 and the outer loadings will be the same as PLSGraph).

To run a CFA in SmartPLS (Or even in PLSGraph, See my explanation here: viewtopic.php?t=1964&highlight=cfa )

Best regards,

Bido

In PLSGraph one LV alone is estimated as if was connected with other LV with the same indicators (try with just one LV in PLSGraph and run the same in the SmartPLS, using two LVs with the same indicators = the correlations between LVs will be 1.0 and the outer loadings will be the same as PLSGraph).

To run a CFA in SmartPLS (Or even in PLSGraph, See my explanation here: viewtopic.php?t=1964&highlight=cfa )

Best regards,

Bido

- Diogenes
- PLS Super-Expert
**Posts:**905**Joined:**Sat Oct 15, 2005 5:13 pm**Real name and title:****Location:**São Paulo - BRAZIL-
**Contact:**

Hi,

In your way, the results will be equal to run a principal components analysis in the SPSS for each construct separately.

It is not wrong, but the advantage of the SmartPLS (way that I suggest) is that the correlation between construct are considered during the estimation procedure, and we could assess the discriminant validity using crossloadings, which is not possible in your way.

Best regards,

Bido

In your way, the results will be equal to run a principal components analysis in the SPSS for each construct separately.

It is not wrong, but the advantage of the SmartPLS (way that I suggest) is that the correlation between construct are considered during the estimation procedure, and we could assess the discriminant validity using crossloadings, which is not possible in your way.

Best regards,

Bido

- Diogenes
- PLS Super-Expert
**Posts:**905**Joined:**Sat Oct 15, 2005 5:13 pm**Real name and title:****Location:**São Paulo - BRAZIL-
**Contact:**

### Re: measurement model

CFA in SmartPLS to comput scores:

[1] If you had a structural model, and the formative LVs were in exogenous position, we could run the model with covariance based on lavaan (a R package - http://lavaan.ugent.be/tutorial/index.html). But, if the purpose is to compute the factor scores, covariance based is not the best choice (see DiStefano et al., 2009).

DiStefano, C., Zhu, M., & Mîndrilă, D. (2009). Understanding and Using Factor Scores:Considerations for the Applied Researcher.

[2] Reference about factor weighting scheme as PCA: Lohmoller (1989, p.42):

Lohmöller, J.-B. (1989).

[3] One example is Asyraf and Afthanorhan (2013), but they did not include all relations in the PLS model (p.201).

Asyraf, W. M., & Afthanorhan, B. W. (2013). A comparison of partial least square structural equation modeling (PLS-SEM) and covariance based structural equation modeling (CB-SEM) for confirmatory factor analysis.

[4] A second example: Gefen and Straub. (2005).

Gefen, D., & Straub, D. (2005). Pls-Graph: Tutorial and Annotated Example.

Best regards,

Bido

[1] If you had a structural model, and the formative LVs were in exogenous position, we could run the model with covariance based on lavaan (a R package - http://lavaan.ugent.be/tutorial/index.html). But, if the purpose is to compute the factor scores, covariance based is not the best choice (see DiStefano et al., 2009).

DiStefano, C., Zhu, M., & Mîndrilă, D. (2009). Understanding and Using Factor Scores:Considerations for the Applied Researcher.

*Practical Assessment, Research & Evaluation*, 14(20), 1–11. Retrieved from http://pareonline.net/getvn.asp?v=14&n=20[2] Reference about factor weighting scheme as PCA: Lohmoller (1989, p.42):

Lohmöller, J.-B. (1989).

*Latent variable path modeling with partial least squares*. Heidelberger: Physica-Verlag.[3] One example is Asyraf and Afthanorhan (2013), but they did not include all relations in the PLS model (p.201).

Asyraf, W. M., & Afthanorhan, B. W. (2013). A comparison of partial least square structural equation modeling (PLS-SEM) and covariance based structural equation modeling (CB-SEM) for confirmatory factor analysis.

*International Journal of Engineering Science and Innovative Technology*(IJESIT), 2(5), 198–205.[4] A second example: Gefen and Straub. (2005).

Gefen, D., & Straub, D. (2005). Pls-Graph: Tutorial and Annotated Example.

*Communications of the Association for Information Systems*, 16, 91–109.Best regards,

Bido