forum.smartpls.com

If you only want to model them as first-order constructs then there is not need to use the two-stage approach.

The following paper shows that it is advantageous to use path weighting for reflective-formative type models. Often the difference is negligible if the lower-order constructs are not highly correlated. Becker, J. M., Klein, K., & Wetzels, M. (2012). Hierarchical latent variable models in PLS-SEM: gu...

1) The error message means that several of your variables have the same name. It seems to be an issue that they names are separated by the same character as your separation indicator. Ideally, you should either put the variable names in "" or connect them with an _ 2) Blank fields should be OK, if t...

Please read: Sarstedt, M., Hair Jr, J. F., Cheah, J. H., Becker, J. M., & Ringle, C. M. (2019). How to specify, estimate, and validate higher-order constructs in PLS-SEM. Australasian Marketing Journal (AMJ), 27(3), 197-211.

1. No that is not a problem. It is only an intermediary model where you need all the paths to reliably identify the composite weights. 2. I think deleting your items is also not a good strategy and of course you your first stage constructs need to fulfill reliability and validity requirements. Regar...

Yes, it is necessary to calculate these statistics yourself. The paper also explaines how to do it and there is an online supplement with examples. For the HTMT, you need to look at the LV correlations table in your first stage model to get the correct numbers for the correlations between first-stag...

I would think that you want to address the sequence of effects and not really stages as in a higher-order model. Thus, you simply draw the model with your sequence of constructs.

I do not fully understand the problem. It also seems to be more like a decision that has to be made by the researcher than a technical issue.

Unfortunately not at the moment. It is a good idea that we will include to our list of requested features.

Should be possible to include multiple moderators for one DV (i.e., Y) with the same moderator variable (X3) as long as they address different predictor variables (X1 vs. X2). You have to make sure that you select the predictor to be X1 and X2. You cannot have two times the same moderating effect (i...

Higher-order construct is the more general term as you could also have third-order or fourth-order constructs.

When the HTMT is larger than 1 it implies that the correlations of items within the constructs are smaller than the correlations with other constructs. That is certainly troublesome and should be investigated more closely. However, as you are using higher-order constructs it could also have other re...

1) Your sample size is quite small for dividing the data into groups. Especially, your second group is quite small. That could explain the non significant effects in that group and also why your MGA does not show significant differences. 2) The sample size limitation also applies to FIMIX. Especiall...

1) Yes, SSO is equal to the number of observations * indicators, because we have standardized data in PLS which is used by the blindfolding procedure. For standardized data the SSO is equal to the number of observations. Every observation is a scaled deviation from the mean (scaled by the standard d...

If your DV is binary the regression techniques that are used by PLS become problematic. It is still possible to run the algorithm and get results, but they would be similar to results from a linear probability model in regression with a binary outcome. Such a model has some downsides over logistic r...