forum.smartpls.com

That’s sounds a little bit strange to me because 66 cases should be enough for such a model. Perhaps there is a variable with to low variance. That means for one item there are almost the same numbers for all cases which causes the failure. Do you use binary coded variables? Use also another algorit...

Indeed, the sample size in the subsample could be too small for bootstrapping.

Did you try another bootstrapmethod (sign change etc.). Sometimes that helps…

Greetings,

Christian

---

---

Hi Sophia, For the rationality of formative measurement please check following paper by Henseler et al. (2009) on pp. 289: https://php.portals.mbs.ac.uk/Portals/49/docs/rsinkovics/pubs/2009-AIM-Henseler-Ringle-Sinkovics-PLS.pdf To use published items for the measurement doesn’t automatically means t...

Hi Sophia, Perhaps it is better to consider your construct as a formative one if it makes sense. You can also check the correlation between the items of the construct or use a factor analysis to get a feeling about the connection between the items which you use for the construct measurement. Then yo...

Here comes an interesting literature for our topic in this post: Author: Henseler, J. Title: PLS-MGA: A Non-Parametric Approach to Partial Least Squares-based Multi-Group Analysis Year: 2012 Pages: 495-501 In: W. Gaul et al. (eds.), Challenges at the Interface of Data Analysis, Computer Scince, and ...

Author: Henseler, J. Title: PLS-MGA: A Non-Parametric Approach to Partial Least Squares-based Multi-Group Analysis Year: 2012 Pages: 495-501 In: W. Gaul et al. (eds.), Challenges at the Interface of Data Analysis, Computer Scince, and Optimization, Studies in Classification, Data Analysis, and Knowl...

In this case you a right! You should not delete an item in one group and leave it in the other group when you compare different groups with each other because the measurement invariance. Moreover your critical values a only marginal below the critical values as far as can see.
Best,
Christian

Normally, you use more than two items for measuring a reflektiv construct in PLS. A recommended number is e.g. 5 or 6 items per construct. If you have such number of items for your measures you can easy delete one or two items for getting better critical values. Perhaps you can use other/better item...

In my opinion you should work further with you constructs. As mentioned before Cronbachs Alpha (CA) tends to be underestimated in a PLS model. Therefore you should rely more on the AVE and composite reliability values. Personally, I would find it a little bit strange to delete a construct at the who...

Please check following post at the end for a possible answer:

viewtopic.php?t=1453&postdays=0&postorder=asc&start=60

Cheers,

Christian

I'm very glad to hear that!

If you search after nice explanations how to perform the evaluation of measurement in a PLS model then you can find some good hints here:

http://php.portals.mbs.ac.uk/Portals/49 ... cs-PLS.pdf

Greetings,
Christian

H0 is the assumption that the groups are equal. That means that you can reject H0 if p-value is ‘smaller’ than 0.10. One explanation for your second question is that your sample size is too small for detecting a significant path coefficient. But the effect size is relatively high. With a high sample...