[Task]: Response Surface method design experiment - Experimental sheet contains impossible negative values

[Lia-UC]

I just want to make a design experiment for RSM analysis where my variables are sugars (0-20%) and Agar (0.1-1.5%).

The results have some minus concentration. Could you tell me what should we do for the minus treatment?

Originally posted by @Lia-UC in #1705

[tomtomme]

still there with
-------- Application Info --------
JASP Version: JASP 0.95
Build Branch: HEAD
Build Date: Nov 11 2011 11:11:11 (Netherlands)
Last Commit: 6245c0ed1a6d4140dd3db208bd4850fb588e24fa

-------- Basic Info --------
Operating System: KDE Flatpak runtime
Product Version: 6.8
Kernel Type: linux
Kernel Version: 6.14.6-2-MANJARO
Architecture: x86_64
Install Path: /app/bin
Platfotm Name: wayland
System Local: de_DE

[JTPetter]

I don't think this has high priority, not even sure I would consider it a bug. Would just require additional input options to specify boundaries.

[JTPetter]

Okay, actually other software gives the same results and this is desired behavior. @Lia-UC the suggested procedure is to use a face-centered design instead (set alpha to face-centered, below the design table). This will result in the axial points (which in the standard design are negative) falling within the specified range. This is discussed here: https://www.researchgate.net/post/Is_it_normal_for_RSM_using_Central_Composite_Design_CCD_to_generate_negative_values_for_some_factors#:~:text=Dear%20Abu%20Saeid%2C,fitting%20within%20your%20desired%20range.