Turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

- JMP User Community
- :
- Discussions
- :
- 3 factor 3 level half factorial DOE

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

3 factor 3 level half factorial DOE

Jan 30, 2019 4:12 PM
(875 views)

I have to produce a model equation for a 3 factor 3 level half factorial in the form of y=B0+B1X1+B2X2+B3X3+B12X1X2+B13X1X3+B23X2X3+B123X1X2X3 using a 3 factor 3 level half factorial. I have never used JMP before but it is required for my class. I am not sure how to get the coefficients for my equation. I have found a lot of information about full factorials but not much for this. Do I use the discrete numeric, continuous, or categorical factors? Does the Taguchi design for work this method?

1 REPLY 1

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: 3 factor 3 level half factorial DOE

Did you design the experiment witih JMP? If so, important and useful meta-data was generated along with the columns for the factors and response. If not, this analysis will still work.

Select **Analyze** > **Fit Model**. Enter the response data column in the **Y** role. Select all the factor data columns, click **Macros**, and select **Full Factorial**. (I am not sure if the half-fraction design will support estimating all these terms but give it a try.). Click **Run**.

See Help > Books > Design of Experiments and Fitting Linear Models for more details.

Learn it once, use it forever!