forum.smartpls.com

I don't know if this is necessary from a calculation point of view but I just had the case that the best out of 10 FIMIX runs showed that it aborted the calculation because it reached maximum iterations. As I understand this case I could have gotten a better result if the max. iterations number was higher. But if the current best solution was one which reached it's maximum after 1000 iterations and all others aborted after 5000 iterations. In that case I would not know that i received a solution which is below the local optimum I could have gotten to.

As an easy solution i suggest to simply write out a line to the log window if one iteration was finished because it reached the max. iterations value.

Hope it's clear what I mean. Please let me know if the problem I described is not very realistic.

Best regards, Jan

Thank you for the suggestion. It is a good idea to report some additional information about the other repetitions in FIMIX.
I think we could easily report the lnL and the number of iterations of each intermediary FIMIX run in an additional table. Thereby, researchers can also investigate if the best repetition was very similar to all the others (in terms of lnL) or if there were large fluctuations.

Sounds good to me :)