TOPIC:

LazStats is a statistical software written for Lazarus/FreePascal by Bill Miller. original source code is available here:
openstat.info/LazStatsMain.htm
My LazStats source code (CodeTyphon version) is available here:
drive.google.com/file/d/1FnAZqaZrhwBYgr9...mmt/view?usp=sharing

I think there is a possible bug in LazStats BlkANOVAUnit or ANOVATestUnit, namely it seems that Post-Hoc comparisons are not working with One-Way ANOVA in LazStats.
I couldn't figure out what is the reason, can somebody please take a look?

Test dataset is here:
drive.google.com/file/d/1qsJE1sOHFYYkizc...dUn/view?usp=sharing
"Etch Rate (A/min)" is a dependent response variable, while "RF Power (W)" is independent input variable.


Could somebody please test it?

At LAB CT ver 7.10
C:\codetyphon\CodeOcean\1_App\TyphonStats\

Good to know that there is CodeTyphon version of LazStats (TyphonStats) available!
However, the code regarding ANOVA post-hoc comparisons is not working properly.

In current LAB CT 7.10 (unpublished)
works OK

Typhon Win64 (Win10 64 Ent)

Current LAB CT 7.10 (unpublished)

Typhon64 on MacOS 10.15.4 Catalina

Hi
I tried with TyphonStats in CodeTyphon 7.10, with the demo dataset given above. Post-hoc comparisons for ANOVA (see attachment) don't return any results, you get only regular ANOVA results without post-hoc calculations...something is wrong with the code for post-hoc comparisons.

Thanks Sir
your OS ?

Win 10, 64 bit

Thanks Sir
we port this project to CT.
If some procedure(s) not work, you have the full source and you can help us.
Always we want help to fix the bugs.