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
- :
- Discussions
- :
- empirical response surface model

Topic Options

- 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
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Aug 28, 2015 11:46 AM
(1092 views)

How can I generate response surface models (empirically derived graphs) using JMP from the data I acquired for the response?

3 REPLIES

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

Your question is not clear...a model is a mathematical equation...a graph is a chart. Can you tell us which you really want?

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

Aug 31, 2015 12:15 PM
(994 views)
| Posted in reply to message from Peter_Bartell 08/31/2015 12:53 PM

Sorry for the confusion, I would like to create the response surface model which means a mathematical equation that fits my data using linear least-squares regression.

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

sdgff:

At the highest level then you'll be accessing one or more of the modeling platforms available in JMP or JMP Pro. There is no 'one size fits all' modeling methodology. Modeling methods have been developed over the years for addressing specific types of practical problems, means by which the data was collected (DOE, happenstance, or some other method?) etc. In general each of these platforms requires you to articulate responses, a model specification, and often times, a specific modeling method. Each platform will produce a model and lots of diagnostics...you get to decide if it's useful for your practical problem. From the sounds of it though you've expressed a desire to use the Fit Model -> Standard Least Squares personality. But there are others too like the general linear models personality that might work too.

I suggest taking a look at the JMP online documentation around Fitting Linear Models to start to get a sense for the best way to proceed: