cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar
mckowalski
Level I

Uncertainty bounds on Surface Plots and saved prediction equations

I've been asking for uncertainty bounds (e.g. confidence bounds, prediction bounds, etc.) on surface plots for years but I don't think it's ever going to happen. I guess it's more difficult to code than I had realized. Regardless, I thought I'd ask again.

 

I also thought I'd mention that it's not always possible to reproduce the uncertainty bounds of a saved prediction equation in the factor profiler. Sometimes you can save the uncertainly equation and get it to work, but it doesn't work for all models such as Generalized Linear Model (GLM) for example. I need to be able to stack multiple prediction equations in the factor profiler in order to see how different outputs behave across the same input domain space. Unfortunately I can't get the uncertainty bounds to come up for all the different prediction equations JMP offers.

2 REPLIES 2
P_Bartell
Level VIII

Re: Uncertainty bounds on Surface Plots and saved prediction equations

With respect to your 'I've been asking...' have you 'asked' on the JMP Wish List within the User Community? If not, you may want to 'ask' there? That way other users can 'vote' on your request...and this much I can tell you...if it get's enough votes...JMP developers and product management staff pay attention to those votes for capabilities to include in new releases.

mckowalski
Level I

Re: Uncertainty bounds on Surface Plots and saved prediction equations

I'm sorry. I thought I was asking on the JMP Wish List. I'm not sure what this is posting to then. I just followed the wish list link and I thought I was making a request. Regardless, thank you for taking the time to get back to me. 

 

I'm not sure if it's worth mentioning here but a quick suggestion WRT wish list acceptance criteria might be to prioritize which suggestions align with the goals of JMP the company first followed by how hard they are to implement. By that I mean that JMP is a data visualization tool i.e. suggestions which are low hanging fruit which enhance data visualization should get higher priority than say requests for more robust computational capability (which the parent company SAS offers through their software). It might make happier customers overall than say, relying on votes on a community page which only experienced users (with advanced suggestions) even know how to access. And please don't read this as a snarky comment, I'm only trying to help. I really like JMP and have used it for years