Functional DOE: Adding Confidence intervals and Enabling Interactive HTML file export

[Steve_Kim]

What inspired this wish list request? 

(1) From 'Functional DOE Profiler' feacture in Functional Data Explorer in JMP Pro, I would like to see

  (1-1) Confidence Intervals   and

  (1-2) Interactive HTML file export from the profiler

(2) From 'Model Comparison' in JMP Pro,

   (2-1) 'Model Averaging' (Ensemble) result showed a fixed RSquare (1.00) and RASE (0.00). I think it's a bug. 

   (2-2) Shelf made 'Ensemble model' that is formulated from other models (Least Squares, Partial Least Squares, SVEM Lasso, XGBoost, Neural Turned with different weight) also showed a fixed RSquare (1.00) and RASE (0.00) value in Model Comparison results. 

What is the improvement you would like to see?

Why is this idea important? 

[Steve_Kim]

(1-1) I have noticed that the confidence intervals of the Functional DOE Profiler was already listed. 

https://community.jmp.com/t5/JMP-Wish-List/Confidence-Intervals-for-functional-DoE/idi-p/413151

(1-2) The functional DOE Profiler has been saved in interactive HTML format using JMP Pro 18 (Graph > Profiler).

[PatrickGiuliano]

Hello @Steve_Kim Thanks for your interest in contributing ideas for future improvement of our FDE platform!

If you have not done so already, can you kindly submit your Request (2) to [email protected] so we can further investigate/ assist you? 

In your email solicitation, please provide the following information if possible: 

1. Your JMP Pro version and your OS/ version. 

2. An example data table in JMP with saved data table script that reproduces your Model Comparison output.  If you can't provide that, then please provide a description or illustration of your modeling specifications for each model being compared, and clear screenshot(s) of your Model Comparison output.

cheers,

-@PatrickGiuliano (JMP Technical Support)

[SarahGilyard]

Hi Steve_Kim. An update on your FDOE confidence intervals request ...  we are currently researching the feasibility. Due to the complexity of the models used, offering an accurate confidence interval with the correct coverage is tricky. We have had multiple requests for this functionality, so we are studying it. 

Regarding the possible model comparison bugs, if you haven't already done so, could you please submit your request to [email protected] so our tech support could further assist you. 

Thanks.