JMP Wish List

With the increase in speed of deployment and usefulness of AI tools like ChatGPT could JMP use this as part of EasyDoE and other platforms to help users design an experiment as well as the analysis   Using a simple chat window linked to the AI it could ask you questions about the factors, constraints etc and this could then use JMP to build up the design of the experiment. Other companies are taking this approach to AI.   AI seems to be the future and integrating it into tools like JMP will be essential for the growth of data analytics in the (very near) future. Not implementing this soon could mean users look elsewhere for the simplicity of interactions with AI.     ... View more

I would like an option in the Distribution Platform Preferences to set standard values for Confidence and Proportion to Cover to be used in Tolerance Interval Calculation.   Similarly, when computing Tolerance Intervals for many by-groups, it would be great if there was an option to specify Confidence and Proportion to Cover only once for all by-groups, because typically in such a situation I want to use the same levels for all groups (or is there a way to this by holding down a key or sth? Using ctrl works only to the degree that the interval is computed for all groups, but each time levels must be specified). Maybe you can supply typical settings as you do for Confidence Intervals, although here it would have to be 3x3 (0.9/0.9, 0.9/0.95, 0.9/0.99, 0.95/0.9, .... ) plus other...   ... View more

What inspired this wish list request?     What is the improvement you would like to see?  An option included in graph builder, like in Summary Statistics for example, to have it generated automatically, in a single click, (taking into account all the  By variables, data filters etc). Then add the letters on the graph, on top of the bars. See image attached for an example of what it may look like.   Why is this idea important?  I believe it'sa must have, since other softwares can do this as standard. Understanding whether means are significantly different from each other to make decisions is a very basic thing to do, but currently it is unnecesarily cumbersome and time consuming. I believ this would benefit very many users.   ... View more

What inspired this wish list request?  Process characterization reports often include prediction formulas and simulations.      What is the improvement you would like to see? Option to include prediction formulas in the easy DOE report export. Also would like to be able to export models/prediction and PredSE formulas to a jmp table from the easyDOE.   Why is this idea important? Because models made by an easyDOE user may need more exploration by advanced users. For example, comparing an easyDOE model to one made a different way, simulations, simple plots against data, etc. Typing prediction formulas with lots of factors is other non-trivial.      ... View more

My chemist collected MSA data using mostly his standard data collection process. The correct and logical model using Fit Model would be: Product Date[Product] & Random Repeat[Product,Date] &Random   My chemist would really like to use one of the regular MSA platforms. But the nested models for them do not allow Date to be nested within Product.   Product should be a fixed factor. It is not a Part in the classical sense.   If I give into my chemist's demands and give him a regular MSA JMP platform result, the calculated metrics are wrong.   I would like the model choices available for the MSA platform to be more flexible. Allow for a fixed term that is not the classical "Part." Allow for more combinations of fixed and random terms in the model beyond just 3. This is a very simple example, but most real examples in my industry have (or should have!) more than 3 factors.   If the correct model was more often available in regular JMP MSA platforms, I could move my chemists and engineers away from Excel templates using the range method. Please, anything to get them away from that! ... View more

What inspired this wish list request?    I've generated a map of a product I help to analyze in the graph builder platform. This map has local data filters and column switcher enabled.  To see the entire area of the product map, I've set the x & y axis to the appropriate range, then used lock scale(1) in the script to make sure they don't change between filter selections. Lock scale also locks the scale of the legend, which is unfortunate when different metrics need to be looked at, and different areas of the product.    What is the improvement you would like to see?    Implementation of different locks for axis and legends.   Why is this idea important?    The purpose of legends is to add further information to a visualization. When it's locked into a range, the purpose becomes defeated because it cannot be fulfilled.   ... View more

Recently ran across this problem.  Needed to fit an exponential growth model to a set of data where the curve must pass/start at the origin. Most of the exponential growth models in Fit Curve don't allow you to constrain the model parameters so that the curve will go through the origin.  So I wasnt' able to do what I needed in Fit Curve.  I was able to do this in Non-linear by building the model I wanted, but that is rather technical and above the level of the typical user who wants to use Fit Curve.  Many chemical and physical kinetic processes y(t) start with y(0)=0.  Currently only Weibull Growth &  One Compartmental Oral Dose have that property.     Could either: a) Allow for fixing and constraining parameters in Fit Curve so that you could get y(0)=0, or b) Adding exponential growth models that go through the origin.  For example, these models would be nice to have y(t) = a(1-exp(-bt))   y(t) = a(1-exp(-bt)) + c(1-exp(-dt))       ... View more

I've been a big fan of equivalence tests in JMP. For a one-sample scenario in the Distribution platform I like the output because it has a nice graphical representation of the equivalence bounds overlaid with the confidence intervals on the mean. You also get a deliberate interpretation statement at the bottom.   In a multi-sample scenario in the Fit Y by X platform it's less interpretable. I was in a meeting with a few engineers, and they had no idea how to interpret the two normal distributions and indicated they definitely prefer the one-sample case.   My proposal would be to create similar output in Fit Y by X as to what you see in the Distribution platform. For the example above, the equivalence bounds of [-6, +6] can be easily shown with a red confidence interval based on the actual output (centered around 3.02). ... View more

What inspired this wish list request?  (edit) Apparently the template drops a bunch of text here.  The inspiration is that selected rows are drawn above EVERY custom user-generated graphics script, regardless of the draw order given.   I understand that the devs were trying to fix the issue of un-selected data points being drawn above selected data points, but they took the lazy fix and just clobbered any hope of having the user determine the draw order.  Now selected points are drawn above everything else.  I'm almost surprised that the mouse is drawn above selected data points.     What is the improvement you would like to see?  (edit as this form dropped my previous response) I would like to see JMP adhere to the draw order given in the graph customizations list.  If a users attaches a graphics script AFTER the marker seg, then any elements drawn by that script should be drawn on top of all markers,  Period.  End of story.     Why is this idea important?  (edit, as this form dropped my first response)  This is clearly important.  Extremely important.  To the point that my org is putting serious resources into alternatives such as Python or online with JS.  There is a large number of work-flows that now cannot be done in JMP14 or 16, full stop.   Consider this graph: Here I might want to highlight a specific item by selecting it in the legend.  When I do, the dense data points completely obscure EVERY SPLINE, even though the splines are drawn as separate scripts AFTER the marker segs.   This is just one example.  In my org it is common to have many thousands or even hundreds of thousands of data points.  Drawing some sort of custom summary graphic above the data points (whether it's splines, goal lines, confidence intervals, or any other such custom graphic) is needed for properly consuming the data.  With JMP14 and beyond, this becomes totally useless for interactivity, since selecting items (and the associated data points) completely obscures EVERY and ALL other graphics drawn on the graph.   And while my org is slow to update to new JMP versions (as many are still using JMP12), I'm left telling people that it's impossible with the new versions of JMP to have the same workflow as before.  Instead of being faster with better features, we're left with something completely useless.   And while I do understand that a user can simply deselect the rows (say by clicking a single data point), this type of work-around to a fundamentally bad design decision by the JMP devs should not be necessary, and is not always acceptable (and also changes the visual story / significance):   From my perspective this is so egregiously bad that JMP should provide a hot-fix and patch all users systems in JMP14 and beyond, not wait till JMP18 to fix.   ... View more

In an unequal slopes ANCOVA model the individual slopes can be estimated with the Estimates > Custom test or Estimates > Compare slopes option in the output for Fit model. Standard errors and p-values are also given but I miss confidence intervals for the slopes. This should also be possible if additional random effects are added to the model (a mixed model). ... View more

What inspired this wish list request?  Past personal need and experience with colleagues who are implementing partial signal analysis algorithms to analyze data.     What is the improvement you would like to see?  Signal processing functions for standard results found in pythons scipy, including filters(digital & analog), FFT (spectrum), noise, convolution, correlations, transformations, peak analysis, SNR, THD, and vibration analysis. If possible I would go further and add functions for simulating signals as well, this would also be great for teaching and well as synthesizing signals for specific needs with good control and intuitively.    Why is this idea important?  I believe one of JMP's major strengths is the low entry level that it allows of it's users to be able to do complex tasks quickly while assure it's integrity and also assist users in gaining a deep understanding of processes.  I feel the area of signal processing lacks this immensely and feel that the folks at JMP can contribute greatly to this field.  This is a major field with increasing traction and I believe this would align well with JMP's renewed emphasis for targeting academia.      ... View more

We often use a contingency analysis to show outcomes across groups. However, there is no visual indication on the plot of confidence intervals, giving users no idea about whether the differences are significant or not. What I'd suggest is more like the 2nd image below. Confidence intervals should be calculated using, for example, Agresti-Coull, Clopper-Pearson, etc (https://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval#Agresti%E2%80%93Coull_interval)   ... View more

I think it might be practical and valuable for some users, if it would be possible to save the data from a distribution histogram into a table. The table would then contain two columns where one is the undersize value (i.e. the upper bin limit), that increases with the bin width that was set in the x-Axis settings of the histogram, and the other column contains N of the respective bin (and/or, or in a third column, the respective recalculated frequency).   Currently, it is possible to get the proposed table, but only using a work-around: One can save the level numbers of the histogram of interest (the levels also scale with the set bin size in the histogram's x-scale) into the original data table. Then one can organize the date e.g. using the command (as described in How to get the table of values after constructing a histogram? - JMP User Community). However, one then still has to manually adjust the levels to the actual x-axis scale that was used in the histogram.   Since there is already the option of saving different data directly out of the histogram under the distribution dialogue menu via (like the levels described) above), it might be relatively simple to implement another option, where the above proposed table is directly created. Especially since the data must already somewhere be stored in JMP in order to create the histogram graph.   This feature might for example come in handy, when particle size distributions have to be recalculated from a number based distribution into a volume based distribution or vice versa. With the new feature, the data of the histogram can directly be manipulated and/or recalculated.   Currently using JMP 16. ... View more

Add a test to produce p values of superiority tests at a range of distances and output those to a table or graph as shown below.   Consider a trial where a process change is made.  Results are compared with current performance and a t test determines that the process was improved (the mean shifted) with a p-value of 0.05 and a superiority test in JMP 17 indicates that the mean shifted by at least 0.01 with a p value of 0.12, but neither tells a whole story.  To make an informed decision, we would want to know information like: 5% chance the process stayed the same or got worse 90% chance the process improved by at least 0.01 50% chance the process improved by at least 0.006 5% change the process improved by at least 0.011 Here is a post with two potential methods of calculating these values: Compare means test: graph probability by difference in means  ... View more

When using 'colour or mark by column' from the 'Rows' menu, one can assign different symbols or colours to different variables, but the graph legend in graph builder does not update to show the reader what each symbol or colour represents (the actual data points update, but the legend does not) - it would be great if we could have the legend update as well to really elevate this functionality.  ... View more

I realize that there is a workaround for doing a Friedman's test, but it is certainly not a big ask to have it in the program.   This is especially true if using it for teaching . ... View more

Now, Expanded Estimates are available only for basic regression models. It would be great to have them for models that are less standard, like logistic regression, ordinal regression, ... ... View more

I have one request/recommendation for a future release of JMP.  In the one-sample equivalence test platform in JMP 16.0.0, I noticed that there is no correction for the non-parametric test case.  Yes I can, in essence conduct the test using the one-sample T-test platform: and by running the Test mean option 2X and picking off the appropriate tests as shown in the graphic below:   But I can’t get the Equivalence region nor can I get the TOST framework formalized in this same way which is what I like about the Test Equivalence Platform for the normality assumed case. So formally the request is for a non-parametric version of the TOST for the one-sample test.    Note that for the 2-sample case I can compute a non-parametric confidence interval on the median difference and compare that to the practical difference region and effectively run the TOST in this way (e.g. Hodges-Lehmann confidence interval on median difference using Wilcoxon all-pairs NP test). This is just the “confidence interval version” of the TOST.  So this actually works quite well for the 2-sample case without any need for an additional feature in the Equivalence Test platform in Fit Y by X.   But in the 1-sample case, in the Distribution platform, I cannot do the same, why? The only way I know of doing something similar to this would be using Custom Quantiles in  JMP's Distribution platform, and that does provide a non-parametric estimate (albeit not the Hodges-Lehmann one, and I have trouble specifying the exact desired coverage for Confidence level of the TOST which is a standard 90% for a 5% significance level).   So (lower-priority) an additional feature altogether could be, the calculation of a non-parametric confidence interval estimate using Hodges-Lehmann on the median in the Distribution Platform. Or perhaps a boot-strapped confidence interval (which you can do for almost every table already in JMP Pro with Right Click > Bootstrap on data table output).   ... View more