The World Statistics Day celebration continues here in the Community. We all need reliable data for sound decision making. Do you have a data source that you trust most? Head over to Discussions to tell us about it.
Choose Language Hide Translation Bar
Level I

DOE Signifikanzniveau test (Anfänger Probleme...)

Hallo Zusammen,


Ich neu und daher nicht vertraut mit dem Programm/Forum, über Hilfe würde ich mich sehr freuen.


Ich würde gerne meine Versuchsergebnisse: Reißfestigkeit,Bruchdehnung, Spannung, Shore-Härte Nah/fern, sowie die Dichte auf Signifikanz zu meinen Versuchsparametern: Anteil Mikrosphären, Werkzeugtemperatur und Dosierweg überprüfen, bekomme aber leider keine vernünfigen Ergebnisse.


Evtl der Falsche Ansatz aber mein Einziger:

(beim Versuch die Hilfe (DOE GUIDE S.51) zu befolgen bekomme ich beim Laden meiner Faktoren die Meldung Keine zulässige Faktortabelle)


Vielen Dank an dieser Stelle schon mal für Zeit und Mühen.


2020-01-11 16_25_43-LTC - JMP Pro.png

Super User

Re: DOE Signifikanzniveau test (Anfänger Probleme...)



That part of the guide deals with designing the experiment, not analyzing.  Loading factors has to do with importing pre-specified factors and factor levels, which is a convenient way to not have to re-input the factors over and over when you are iterating through several design options.

You need to use Fit Model of another analysis platform from the Analyze menu to perform the analysis on your results.  In the dialog for Fit Model you will specify the model terms you want to fit to your DOE data. See the Fitting Linear Models guide in the Help menu for further direction.

-- Cameron Willden
Level VI

Re: DOE Signifikanzniveau test (Anfänger Probleme...)

I think there are three rules for successful data analysis:


1. Plot the Data.




As a precursor to using the Fit Model platform as recommended by @cwillden , I recommend using Graph Builder or the Fit Y by X platform and create the following plots asking these question:


1. Do the results make sense from a process knowledge point of view?

2. Are there outliers or suspicious looking observations that will make subsequent analysis problematic?


Use Graph Builder or the Fit Y by X platform...


1. Each factor vs. response (a scatter plot).

2. The response(s) histograms.

3. The response(s) in experimental execution order.

Article Labels

    There are no labels assigned to this post.