JMP Wish List

hogi · ‎11-04-2022

☐ cool new feature ☐ could help many users! ☐ removes a „bug“ ☑ nice to have ☐ nobody needs it Please allow the user to send dt << Get nonExcluded Rows(); to a data table to get a matrix of all row numbers of non-excluded rows. Please make the implementation as fast as dt << Get Excluded Rows(); https://community.jmp.com/t5/Discussions/col-lt-lt-get-values-for-non-excluded-rows/m-p/556579/highlight/true#M77051 The fastes single-line command that was posted in the community is almost an order of magnitude slower: allRows = dt << get rows where( Excluded() == 0 ); https://community.jmp.com/t5/Discussions/col-lt-lt-get-values-for-non-excluded-rows/m-p/564380/highlight/true#M77688 And first asking for the non-excluded rows and then "inverting the list" adds 30-50% to the time budget. https://community.jmp.com/t5/Discussions/col-lt-lt-get-values-for-non-excluded-rows/m-p/564136/highlight/true#M77669 more wishes submitted by

Steffen_Bugge · ‎11-04-2022

I suggest adding the 'new formula columns' option to the response table in the Easy DOE platform. If the response in a DOE is measured repeatedly, it would be beneficial to have the possibility to add all the data to the response table and generate a new formula column for the average response. The 'new formula columns' option could also find other practical applications in this platform.

winfriedkoch0 · ‎11-04-2022

To visualize my wish I have used the Big Class Data Table and run Fit Model and the Prediction Profiler. Then I have done two changes for a nicer report: - Changed the label orientation of the x-axes to horizontal, - In the Effect Tests Table reduced the numbers of decimals in two columns from 4 to 2: When I now started working on the model and e.g. removed the variable age in the Effect Summary Section and entered it again then the effect of the two settings described above disappeared and the original settings appeared again. In my real working more complex scenarios apply for which the effort spent and lost is considerable. Is there a way to maintain settings e.g. of axis labels, numbers of decimals and others when developing models e.g. by adding or removing variables?

hogi · ‎11-02-2022

HeatMap in Graph builder is a great way to visualize data: https://community.jmp.com/t5/Learning-Center/Creating-Heat-Maps/ta-p/271828 Individual "tiles" can represent several rows of the data table (geographic region: data of many countries). Then the values of the rows are averaged automatically. This is very convenient - but "averaging" (mean) is just one option ... If the user wants to do different aggregations, he has to generate a summary table or use a formula column with exactly the same grouping settings as the desired heat map: https://community.jmp.com/t5/Discussions/Heat-Map-Aggregate-Function/td-p/269522 A more straight-forward and flexible approach: In GraphBuilder/Heat Map, please provide a menu to select the aggregation method: - median - any item from the summary table menu: dt =Open( "$SAMPLE_DATA/Big Class.jmp" ); dt:height[32]=500; Data Table( "Big Class" ) << Graph Builder( Size( 336, 478 ), Graph Spacing( 4 ), Variables( X( :sex ), Y( :age ), Color( :height ) ), Elements( Heatmap( X, Y, Legend( 4 ) ) ) );

jszarka · ‎10-31-2022

Using covariates in the design is a nice, flexible tool to utilize. Sometimes I 'hack' the system in a way where there are 3 covariates available but in reality they are standard 'factors' from a DOE perspective. When I load them into Custom Design, I have the option to make either all 3 covariates as Hard or Easy to change. In some instances, I'd want more flexibility to make it a mixture of Hard and Easy to change variables (e.g., X1 is Hard, while X2 and X3 are Easy.)

hogi · ‎10-23-2022

☐ cool new feature ☐ could help many users! ☐ removes a „bug“ ☑ nice to have ☐ nobody needs it In the NewFormulaColumn/Transform menu there are many useful functions, but a simple rescale function is missing. The idea: a window opens and the user can enter a scaling factor. then a new column is created with the rescaled vales. If more than one column is selected, let's say N, the window contains a list of N number edit boxes. There should also be a checkbox to tell the function to use the first rescaling factor for all new columns.

hogi · ‎10-21-2022

☐ cool new feature ☐ could help many users! ☐ removes a „bug“ ☑ nice to have ☐ nobody needs it In a script window, the user can right click on a function and click on "Help Scripting Index". This opens the Scripting Index with the function selected. my wish: A Keyboard Shortcut to open the Scripting Index with the function selected. https://community.jmp.com/t5/Discussions/Keyboard-shortcut-for-quot-Help-Scripting-Index-quot/m-p/558962/ (no shortcut will be used more often than this one : ) more wishes submitted by

jszarka · ‎10-19-2022

I like the Extrapolation Control available in the Prediction Profiler starting in JMP 16. It is very powerful as both an 'on' and 'warning on' option. Extending this feature to the Contour Profiler would be useful. Because the axes can easily be adjusted in this graph, misleading interpretations can be made as the shading will still apply to the 'lo limit' and 'hi limit' values. My hope is the same logic can be used and that it is an easy(ish) add!

Gschwind86 · ‎10-19-2022

I would wish to have more functionality on the 3D scatterplot. (Exactly as in the Software origin). Where uppon a double click, I can add easily legends, labels, change color of markers etc). Very important also being able to change individually color/size/font of different labels of he datapoints (just double clicking the label and being able to make changes, individually).

hogi · ‎10-19-2022

Tabulate cannot handle columns with modeling type "multiple response": https://community.jmp.com/t5/Discussions/tabulate-and-multiple-response/m-p/557674/highlight/true#M77131 With version 17 of jmp, Graph Builder will support culumns with modeling type "multiple response". So people will start to use this feature more and more often. The problem: Columns, for which modeling type "multiple response" will be enabled, will "disapear" in tabulate. So, there users will feel some pain when deciding which way to go: - cool new Graphbuilder features? - column still useable in tabulate alternative to "enabling support for multiple response" mode: just show the columns as if they were "nominal" mode.

Draj86 · ‎10-18-2022

Bioequivalence testing is an essential step during the development of generic drugs. Different methodologies are used depending on the requirement. For e.g, in the EU, EMA recommends using average bio equivalence test (ABE), while in the USA, FDA recommends using population bio equivalence (PBE) test. Both methods present some limitations. alternatively Bodin et. al., AAPS journal 2020 proposed method to evaluate bio equivalence: between-batch bio equivalence (BBE). It is based on the comparison between the mean difference (Reference − Test) and the Reference between-batch variability.

winfriedkoch0 · ‎10-15-2022

In ordinal logistic regression the odds ratio (under proportional hazards assumption) is the usual measure of effect size. This odds ratio is available in nominal logistic regression but not in ordinal logistic regression. It can be rather easily calculated from parameter estimates but I would appreciate that this additional step be available in JMP.

hogi · ‎10-13-2022

☐ cool new feature ☐ could help many users! ☑ removes a „bug“ ☐ nice to have ☐ nobody needs it The code in the formula editor can be either constructed by clicking on variables, columns or function in the menu on the left, by dragging items into the formula window - or directly by typing in the code. In the latter case, after typing in the first character, a small jsl code editor pops up and the user can continue to enter the code. There is even syntax highlighting :) Unfortunately, it happens very often that the second - or even third - character is lost: Do other users experence the same issue? What's the benchmark typing speed? 3 missed characters? I hope, the issue can be fixed in a future release of jmp :)

shampton82 · ‎10-12-2022

I'd like to see the columns that are causing the error to show up in this error message: right now it is quite tedious to find out which columns to remove to get past this error. Note: this was while using the BSF platform.

hogi · ‎10-12-2022

☐ cool new feature ☐ could help many users! ☑ removes a „bug“ ☐ nice to have ☐ nobody needs it JSL auto suggestion via object << xy + CTRL + space is great. But it takes very long for the auto suggestion list to be generated if the user presses CTRL + space and (*) - JMP doesn't know the object yet - no first letters (xy...) were given Some ideas how the behavior of JSL auto complete could be changed: - make the generation of the list faster [esp. for the unique case "show all commands" (*)] - allow the user to agort the generation of the list by click somewhere with the mouse or pressing esc. - in the case of (*), generate an empty, list - without waiting time. - in the case of (*) instead of generating a list, fill the Hover Window with a text that says that 1) the object was not defined yet and that 2) the user should enter at least one letter of the command

AmyBurgess · ‎10-10-2022

Following an analysis e.g. linear regression I often use the "make into data table" function. The output table changes the data from it's original format e.g. from "Numeric" and "Continuous" to "Character" and "Nominal". It also renames sometimes e.g. from "Concentration" to "Group". This means, in order to create new analyses from these tables I have to manual change the titles and data formats back to their original settings. Can we make it so that data formats and column names are retained from the original data table? JMP 16.1.0 Example: Original Column settings: Analyze > Specialized Modelling > Fit Curve Fit Curve > Polynomials > Linear Inhibitor Concentration is now “Group” Make Data Table I want to plot Slope vs Inhibitor Concentration but the column is “Group” and the Data and Modelling Type is no longer correct.

lweiss1362 · ‎10-07-2022

In the "Fit Model" platform, I think it would be great, if in an update or future release, one could add a variety of spline transformations(including natural cubic, bspline, or pspline with the ability to select the placement of knots). There are times when I need to do some nonlinear count data modelling with random effects (ie ZINB, Hurdle, ZIP ... ) that requires GLIMMIX or NLMIXED in SAS, but it would be great, for instance, to be able to have the same flexibility for the “fit model” platform in JMP to do the same. Also if the starting parameters could be output that would helpful too. Due to the speed of processing it could serve as a check on the results of both NLMIXED and GLIMMIX.

Charlie · ‎10-05-2022

I have a stacked table with a Time Point (X) column, a Cumulative Release (Y) column, and several columns of factors from a DOE. We have different specification limits for release at various time points in the dissolution curve, as required by the FDA. In development, I need to fit curves to the data, use models to determine significant factors, and optimize factors using Desirability Functions. I can fit curves with this table, but I cannot use the Desirability Functions because each column can only have one set of specifications saved with it. I can split the table by Time Point and make a new table, but that creates more documentation and review work, as required by our data integrity rules. It would be nice if there was a way to account for these specifications in Fit Model and FDE. Suggestions Allow specification limits to be set conditionally. This may help resolve the problem for non-FDE models. In FDE, allow more than one target curve. Curves based on upper spec, target, and lower spec would allow explorations of the variable space for each target curve. I use JMP Pro 16.2.0

egon_gross · ‎04-19-2018

Hello, I got JMP 14 installed on my desctop from our IT department recently and wanted to change the standard icon on the desctop by "right klick-properties-change Icon/ symbol". Unfortunately this didn't work as administrator rights are necessary to perform this procedure. As I participated in the early adopter program (and will continue to do so) it would help a lot to distinguish the program of choice right before starting the program. As the modification of the desctop icon is not such a fundamental change it would be nice to get this done even without admin rights. Yours E. Gross

d_barnett · ‎04-18-2018

When you create a model using the DoE platorms there is the option to simulate responses prior to the table being made but when you run the model script you have generated the :Y response is included, this means you have to change the model to use the :Y simulated responses you have just generated. The idea is that if you Simulate Responses during the generation of a model the ':Y Simulated' should be included into the model dialogue, not the ':Y' David

JMP Wish List

data tables: get non-excluded rows

New formula column in response table of Easy DOE platform

Maintain settings eg in Prediction Profiler

Heat maps -> median aggregation [and more]

Covariate Design Flexibility between Hard and Easy to Change

add "rescale" to new formula column right click menu

Keyboard shortcut to open Scripting Index on the correct page

Extrapolation Control for Contour Profiler

Upgrade 3D Scatterplot functionality

enable "tabulate" support for columns with modeling type "multiple response"

Add Between batch bio equivalence testing proposed by Bodin et. al., AAPS journal 2020

Add an odds ratio in ordinal logistic regression analysis

fix the "2nd character issue" in the Formula Editor

More information in error message for variable importance

JSL auto suggest: improve waiting time

Data Tables from Analysis - retain name and data attributes from previous table

Spline transformations in Fit Model

Using Multiple Time Point Dissolution Specifications with Models

Enable easy modification of desktop icon without admin rights

:Y Simulated Responses values used in Model Dialogue not :Y