JMP Wish List

Benjamin_Fuerst · ‎02-04-2022

Hello, It would be very helpful after punching in the linear constraints for a DOE, to see a preview of your constrained space before you "Make the Design". Ben

ttallen · ‎12-03-2021

I am a big fan and user of the Custom DOE option in JMP. I recently use the option to plan a pro COVID vaccination advertising campaign that significantly increased rates. At the same time, I wish that the software included expected bias (at least as an option) in the design criterion. Both Doug Mongomery and I have written papers about variance plus expected bias criteria. George Box pointed out the importance of including bias in experimental planning optimization. For related references please consider our old article: Allen, T. T., & Tseng, S. H. (2011). Variance plus bias optimal response surface designs with qualitative factors applied to stem choice modeling. Quality and Reliability Engineering International, 27(8), 1199-1210. Variance plus bias optimal response surface designs with qualitative factors applied to stem choice modeling (researchgate.net) It shows how to make reasonable assumptions in general situations. Contact me at allen.515@osu.edu if you want to discuss this.

rc_hertzy · ‎06-19-2021

While many JMP methods are described or identified in platform output (e.g., Nonlinear saying "Solved by Analytic Gauss-Newton") others are not. When different JMP platforms give different results, understanding and explaining that difference is difficult. My client (US government) uses confidence limits for policy decisions, so I need to know why the methods differ. Example (JMP 16.0.0): Nonlinear vs. Fit Curve, both using Exponential 3P model, even though the corresponding parameter (and Std Err) estimates agree to the number of digits shown. Extremely useful would be JMP having a central Help page where one can easily locate the identification of the statistical method employed. Including a reference and/or summary of the statistical details would also be helpful.

Vins · ‎05-01-2021

The covering array DOE platform now supports dissallowed combinations. Based on a talk by @joseph_morgan and @Ryan_Lekivetz a few years back, the availability of options in the covering array platform that allow you to set different factors at different strengths would greatly improve the platforms use and applicability in software testing and laboratory testing. A JMP add in would also be welcomed.

jszarka · ‎04-27-2021

When generating a split-plot or other experiment with random blocks using Custom Design, I really like how the resulting data table has an Evaluate Design script already attached to it. However, if I update the 'Whole Plots' or 'Random Block' to actually reflect what it truly means in practice (e.g. Setup or Batch) then the script doesn't work. I think it's as simple as adding that linkage (as denoted by the ":" that you get with the other factors). If I just have X1-X3, this is what the code looks like for a split-plot, and won't update once the Whole Plots column is renamed. However, if I update the name of X1, it will update appropriately. DOE( Evaluate Design, X( Whole Plots, :X1, :X2, :X3 ) )

shampton82 · ‎01-10-2021

I'd like to see the process screening platform be able to recognize columns assigned as non-normal and be to use these columns in the analysis. Right now only normal data columns can be used.

plebrun · ‎10-09-2020

There is two main schools of how people can build DOE. The one chosen by JMP is to create design matrix using the powerful coordinate exchange algorithm. The second way is to provide a list of candidate data points (that could respects some complex constraints) and then search through it to create the design. (Actually, is JMP creating this list of candidate points in background ? When looking at design, there are some weird non rounded values, some times, which seems to indicate that JMP can take really any point (satisfying constraints if any) from the space of factor.) I discussed yesterday with many DoE users at a conference, and they told me the fact that the second option does not exist in JMP is one of the main reason they don’t want to buy and use JMP. This option is however available in SAS proc Optex, which I am sure share many similarities with the Custom DoE platform of JMP. Would you think such addition may be possible in the future, for Custom Design and Augment Design platforms ?

Amir_H · ‎03-30-2020

Can you please fix the HTML interactivity in DOE model's profilers when one or a few constraints are defined? My DOE model’s profilers in the HTML file became static when I added the constraints. They were interactive when I had no constraints. Unfortunately, including constraints in most DOE models is inevitable.

MathStatChem · ‎10-22-2019

I would like the ability to get alias effects matrix using JSL in Custom Design. there is a <<Get X Matrix (X) that returns the design matrix for the specified model and there is a <<Get Alias Matrix message that gets the aliasing correlations (for model x alias interactions, X`*A) but there is not command to get the alias effects matrix for the design (A) In Custom Design, Evaluate Design, and Compare Designs, I would like to be able to use JSL get the full correlation matrix that is used to construct the color map on correlations. So a <<Get Correlations Matrix message would be nice.to add. For Evaluate Design, I would like to be able to see a list of the pairwise correlations of the model x model, model x alias, and alias x alias correlations. Similar to the pairwise correlations table that can be displayed in Multivariate. The reason so so that I can sort and see the pairs of effects with the highest confounding. For Compare Designs, I would like to be able to see the difference in the effects and aliases correlations matrices. So if I compare 2 designs, and each has a color map on correlations (C1 and C2), I want to be able to see (C1-C2) as a "delta color map".

jdv · ‎10-10-2019

It would be very helpful to allow an option for non-linear constraints for mixture DOE.

JMP Wish List

DOE with constraints: Graphical preview

Custom DOE With an Integrated Variance + Expected Bias Option

Help page for statistical details of all JMP methods

variable strength covering arrays

Labeling Flexibility for Split-Plot and Random Block Experiments for Evaluate Design

Update to Process Screening platform

Custom design from candidate points

Interactive HTML with constraints

DOE platform improvement suggestions

Non-linear constraints in DOE