JMP Wish List

What inspired this wish list request?    In order to avoid incomplete/misleading interpretation of graphics by exactly superimposed measuring points, JMP allows for an automated jittering of such points, usually along a horizontal line. When trying to connect ALL of these (jittered) points by using the “parallel” tool, JMP connects the “central” points only, neglecting all the other jittered/shifted points in the immediate neighbourhood (see graphic below). – Is there a remedy for this “bug”? Many thanks         What is the improvement you would like to see?        Why is this idea important?  Scientific quality of figures. Avoidance of artifical ommission / neglect of interrelationship.   ... View more

What inspired this wish list request?    I made a plot using graph builder (x and y variables plus  an 'overlay' variable). I applied a colour scale to the points/overlay variable but it treats them independently! For example with the rainbow colour scheme i applied i get this result:   What is the improvement you would like to see?    What I'd really like to see is that the line colours are representative of the colour of the dots/data points that they are fitted through. So my green lines should really be blue/purple, and my green dots should really be red/orange.    Why is this idea important?    Because as it is it just looks weird and makes it more difficult to interpret.    ... View more

What inspired this wish list request?  I often run contrasts for many measured variables and have to reenter the contrast coefficients for each variable. This is extremely time consuming. It would be nice to be able to recall coefficients previously entered from a drop down menu or red triangle   What is the improvement you would like to see?  ability to save contrast coefficients to reuse with other variables   Why is this idea important?  Saves time and prevents mistakes   ... View more

What inspired this wish list request?  I want to be able to create project files using workflow builder so that when I need to add new data or edit database, I can rerun the workflow to generate and replace a project file with a new version   What is the improvement you would like to see?      Why is this idea important?  I prefer to save my data as project files (.jmpprj) and would like to be able to generate and save projects using workflow builder.   ... View more

  What inspired this wish list request? JMP does not seem to have a built-in support for zero-inflated models?    What is the improvement you would like to see? Possibility to fit zero-inflated model in JMP   Why is this idea important? It occurs quite often that the response is zero-inflated. Zero-inflated models are used when the response variable has a large number of zero values and a continuous, non-negative distribution for the non-zero values. Zero-inflated models combine two separate models: one for predicting the probability of a zero outcome, and another for predicting the non-zero values.     ... View more

What inspired this wish list request? I analyzed the data in a split-plot design and in the post-hoc test (LSMeans Differences Student's t) the levels by default were arranged according to the least Sq mean. I tried to sort them based on levels and for individual tables; I got success. But I want to know how we can change these settings (sort by levels) by default for all analyses.      What is the improvement you would like to see? Here is an example of how to do the sorting using JSL Names Default To Here( 1 ); dt = Open( "$SAMPLE_DATA/Drug.jmp" ); obj = Fit Model( Y( :y ), Effects( :Drug, :x ), Personality( Standard Least Squares ), Emphasis( Effect Leverage ) ); myobj = obj << Run( :Drug << {LSMeans Student's t( .05, Connecting Letters Report( 1 ) )} ); objr = obj << report; Report(myobj)["Response y","Drug","LSMeans Differences Student's t",TableBox(1)] << sort by column( "Level", ascending = 1); this is a possible solution with JSL but again this is time consuming. therefore preferences setting to have the table sorted by level automatically after the post-hoc analysis   Why is this idea important?            ... View more

What inspired this wish list request?  See the attached screenshot No. 1. The table has two Nominal Columns, "Passenger Class" and "Sex", as Grouping Columns. I may feel like seeing the total number of rows across "Passenger Class" groups, and check "Add Aggregate Statistics." Then I will have "All" both in "Passenger Class" and "Sex", and the table looks miserably cluttered.   What is the improvement you would like to see?  In this case, I would like to have summary statistics only for "Passenger Class", but not for "Sex". In general terms, I would like to have "Aggregate Statistics" for specific Grouping Columns.   Why is this idea important?  Sometimes we need some summary statistics while keeping the table simple and clean.   ... View more

According to Ph. Eur. 5.3 (Statistical analysis), confidence intervals for the relative potencies (REP) may be estimated for parallel line (paragraph 3.2.5), slope-ratio (paragraph 3.3.5) and sigmoid curves. For the parallel line model, a standard error (SE) value can be obtained for the REP values, but not a 95% confidence limit. Would it be possible to also obtain those values? Additionally, how can REP along with their SE or Confidence limits be calculated using the slope-ratio model?     ... View more

Hello, When porting the output data from Matched Pairs to a (combined) data table, the various parameters are split into multiple columns. This makes the data cumbersome to use. It would be preferable for the various parameters (Mean Difference, DF, t-ratio, Prob > |t|, etc.) to be put into separate columns (with the appropriate column headers). Alternatively, they should be tabulated as stacked, with the headers in a Label column and values in a Data column. Once the data is available in one way or the other, it can be handled more easily. With the current approach, it's neither here nor there.   Regards Mehul Shroff ... View more

Hello,   Can Nonlinear be enhanced to provide confidence intervals around the parameter values and a measure such as sigma (as is provided for Fit Parametric Survival) and R^2 (I know R^2 may have limited / restricted applicability so sigma might be better). This is available in competitor tools. Regards Mehul Shroff ... View more

What inspired this wish list request?  When building complex models based on large number of collinear/correlated variables, there are several possibilities available. One of them is transforming the variables into principal components, and then create a model based on these principal components to avoid collinearity issues, reduce dimensionality and keep a large part of the initial information. The problem that could happen in predictive modeling is data leakage : information from the validation set and/or test set is used in the pre-processing and/or model building. This can happen in PCA platform if validation/test rows are not hidden and excluded : if the PCA is done on the whole dataset and after models are built on the training principal components data, the model still contains a part of the information from the validation and test sets. Model evaluation can become biased as the performances would be assessed too "optimistically".   What is the improvement you would like to see?  As for other platforms (see Fit Model below), I would like a validation role when launching the PCA platform dialog, so that the PCA is created with the training rows, and applied on validation and test rows :      Why is this idea important?  The validation role for PCA would enable user to be more aware of this data leakage situation when they are building predictive models. It's also part of the best practices to split the dataset first into train/valid/test sets before doing any transformation/model, so adding this validation role would enforce a reliable best practice for users. Finally, it would be also easier to use PCA in a more reliable way as a pre-processing step for predictive models with this feature, instead of manually or scripting excluding rows.   ... View more

What inspired this wish list request? When using Multivariate platform and using "Color map on Correlations" and any other of the non-parametric color map on correlation (Spearman, Kendall or Hoeffding's D), the colors in the scale are reversed : For parametric color map, by default positive correlations are in red, negative ones in blue :   For non-parametric color maps, by default positive correlations are in blue, negative ones in red (reversed color scale) :   What is the improvement you would like to see? I would prefer having the same color scale/code for both type of correlation map : red for positive correlations, blue for negative ones. The colors difference between the two type of correlation maps can be misleading.    Why is this idea important? This issue should not be a big problem to fix, and would enable to have consistent color scales for correlations by default for all users. It would avoid any manual reformatting (or JSL scripting). This problem is also highlighted when reading the JMP help : Multivariate Platform Options (jmp.com), where both color maps should have the same color scales : "on a scale from blue (+1) to red (-1)".     ... View more

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

What inspired this wish list request? Thanks for updating the interactive HTML output (File > Export >  Interactive HTML with data) in JMP for sharing results with colleagues! I use it many times and it really is a great feature! When I create a scatterplot matrix based on simulated data I like to filter my data. I can do this also within the HTML file output with the mouse by drawing a rectangle across the data points.     What is the improvement you would like to see? It would be much more intuitive to do this via the Local Data Filter. This feature is however not interactive in the HTML output. Could you fix that?     Why is this idea important?  Easier data & result sharing; onboarding new people to JMP       ... View more

What inspired this wish list request?    I look at a lot of manufacturing process data, and often the data sets are very big, but sometimes we are interested in a relatively small number of data points.   What is the improvement you would like to see?    It would be really cool if graph builder had this 'floating reference' line functionality, where you could add it and drag it about to where you're interested in order to easily see the associated values for each line - particularly useful if you have 'stacked' y-axes in graph builder - something i find i'm doing more and more.      Why is this idea important?    could be useful for anyone exploring time-stamped data ... View more

What inspired this wish list request?  I have a column with a specification say, LSL=3. I select "show as graph reference" property. In the graph builder i see the line and it's label as LSL, but not the value.    What is the improvement you would like to see?  It would be great to see LSL=3, not only LSL.   Why is this idea important?  It will create a more meaningful visualization and save time. At the moment I am doing it manually.    ... 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?  StepWise Fit incorporates statistically invalid correlations into the model fit when there are a large number of parameters which are fit. JMP Stepwise criteria is only looking at Sum of Squares along with the F Ratio to produce what stays in the model.  Then only when you Make and Run the final Stepwise Model do you get the Fit Group Effect Summary that gives you the option to get FDR Logworth and FDR PValues. An FDR alpha should be the default input for StepWise rather than the current inputs.    We had to research why JMP is failing to select the correct criteria for incorporating parameters into the fit. Project Euclid (https://projecteuclid.orgtalking)  talks about incorporating FDR in Stepwise and we implemented into Python since JMP could not perform this properly.      What is the improvement you would like to see?      Why is this idea important?      ... View more

What inspired this wish list request?  Common experience while modeling mixture data     What is the improvement you would like to see? When I import mixture data from Excel or another source, then proceed to analyze them using Fit Model and defining the variables as mixture, the JMP profiler in the model output doesn't work properly.  The way to fix that problem is to go back into the data table and separately define eact component as a mixture variable.  It would be convenient and less confusing to JMP users if Fit Model, upon being told that a variable is a mixture variable, would automatically set that definition.     Why is this idea important? Failing to make this change will result in new users coming to wrong conclusions about component traces along Cox axes.  Worse yet, it may cause some users to abandon JMP in favor of other software packages where this is not a problem.     ... View more