forum.smartpls.com

Maybe you can enhance the error message in this case or even put a dialogue before running an MGA. I lost only a few minutes but it would be frustrating getting this message after a 5k bootstrap run that took several hours.

BR, Jan

I know it is currently not possible but since this is the req. feature forum, why not ask for it, I thought ;) Getting the Q² is definetly a help but calculating q² effect strength by hand (http://forum.smartpls.com/viewtopic.php?f=5&t=3376) is a bugger. Having a feature implemented that does it...

Hi Laura, first I think you mean reflective and not restrictive. you ask on how you can change it from a technical perspective? If yes, simply right click on the construct and select "change mode of measurement model" you'll see the arrow direction is changing and now pointing on the indic...

The current method of coppying to Powerpoint as an image is nice but sometimes requires me to rebuild the model by hand as to better fit the Powerpoint look and feel. If there is a way to build such a copy/paste structrue within smartPLS i'd apprecate that

Good to hear, Prof. Ringle! I'm glad I can help :)

Would be pleased to get some feedback on the two methodical questions, too, though.

BR, Jan Schreier

Dear Forum-users, since the available info on holdout samples with PLS-SEM - to my knowledge - is relatively limited, I tried to produce something for myself. So i created a macro with which you can easily take your models outer weights and the path cofficients and run this against the holdout sampl...

Dear All, Having read almost all postings and most of the proposed literature on Multi-Group Analysis (MGA) I still don’t feel like knowing 100% how to proceed for comparing two groups. So I thought I’m not the only one in need of a basic step-by-step procedure. My current understanding of how to co...

For those calculating larger samples in Bootstrapping or MGA you might run into the error: OutOfMemoryError: Java heap space The solution is to edit the smartpls.ini file in the installation directory and increase the values of the following parameters: -Xmx512m -Xms256m to higher values such as : -...

Excellent :)

To me it sometimes happens that I want to calculate subgroups of a dataset but don't need the results of the overall dataset to be calculated. Right now one cannot stop this from happening which is a bit of a hassle, especially when running bootstrapping algorithms. My personal workaround is to impo...

I just saw that the latest smartPLS version (3.1.7) now has this feature. great :) (you can select the weighting vector in the run-dialogue in a new tab called "Weighting"). Is there any documentation of how exactly the weighting is done or are there any papers that describe these procedur...

I finally did a small video to describe the basic algorithm and also updated the file. Maybe it's useful for somebody struggling with understanding the algorithm:
https://www.youtube.com/watch?v=wGjIFC1HlHk

All the best for 2015 to all of you :)

Jan

Currently smartPLS 3.1.6 assumes that the min value is the worst value and the max value is assumed to be the best value in terms of IPMA. I would appreciate having a switch where this setting can be reversed. E. g. the min value is the best value. It's not a big issue for me but might help others a...

Dear Jan-Michael,

thank you for your help. That was exactly what I missed.

Many thanks to both of you for your help and patience!

Jan

Thank you for the advice. I had the Lohmöller at my hands but the WiSu paper is much easier to interpret. My main issue is/was that smartPLS provides in the stop criterion report always the weights and not the loadings (even if all latent variables are measured in Mode A). Is there any reason for th...