New in JMP^® 15 and JMP^® Pro 15

The new features in data tables and graphs, collectively called informative decoration, offer even greater understanding in fewer clicks. Histograms are now presented above each column, and function with the same interactivity of histograms throughout JMP. Histograms are also provided in local data filters, to better inform your filtering decisions. Finally, graphlets, textlets and gridlets provide context while keeping you in the flow of the analysis. Graphlets are supported in the Principal Components, Process Screening and Multivariate Control Charts platforms.

For many users, each analysis begins with importing any of a variety of file types. Data lives in many places, and JMP helps you spend more time analyzing data, and less time importing it. In JMP 15, wizards have been added to process data in XML, JSON and .pdf formats. With a few clicks, you can specify import options and bring these files into JMP.

The .pdf import wizard identifies tables in .pdf files, streamlining the process of importing .pdf content into JMP. You can combine all tables into a single table, create tables individually or combine select tables.

The built-in XML and JSON importers can handle nested and complex files.

The primary graphing platform in JMP keeps improving. Enhanced Graph Builder in JMP 15 means new graphs, including time-series forecasts, more customization options for existing graphs and the ability to drill down for more detail using graphlets. Graph Builder has many other enhancements in JMP 15, including:

• Line of Fit: Save formula of fit. Create two new fits, Robust Cauchy and Time Series Forecast.
• Smoother: Save Smoother formula, improved handling of log transforms and more control over bumpiness, as well as better matching Bivariate’s smoother.
• Four new preferences in the font preference group: Graph Label, Legend, Graph Title and Caption.
• New Histogram and Contour types.
• Additional customization for Heatmaps, Treemaps and Boxplots.
• Extended capabilities for the Line element, including the ability to make Area plots.
• In axes, better default behavior near zero, better handling of log axes in heatmaps. 
• Upgraded Variability chart and Oneway axes.
• New summary statistic for percentage of grand total.

Data cleanup remains the most challenging and time-consuming part of the analytic workflow. JMP 15 simplifies the process by making it easier to recode column names, implement custom sort orderings and automate the recode process.

Virtual Joins have also been improved, allowing a single column to be used both as a key and a reference and new hover tips to determine a linked column's source table. Additionally with virtual joins in JMP 15, when one of a linked set of tables is opened, the others can be automatically opened as well.

The DOE platform in JMP is world-class, better enabling users to solve challenging problems in a wide variety of real-world settings. In JMP 15, numerous improvements to the DOE features have been added, enabling users to create better designs more quickly, and analyze them more easily.

Group Orthogonal Supersaturated Design (GO SSD) is a new platform to create and analyze supersaturated designs. In a GO SSD, factors are placed into groups: factors in the same group are correlated but they are uncorrelated with any factors in a different group. Unlike other supersaturated designs, JMP can treat the first group of factors (containing unbalanced columns) as unused factors.

Also, in JMP Pro 15 the custom designer can now be used to design functional response DOEs, where at least one response of interest is not a scalar, but a function.

Explore Patterns is a screening utility that investigates data integrity and can help you identify unexpected patterns in data. The platform looks for duplicate series of values, linear relationships between columns across groups of rows, properties about the formatted values and certain distributional properties. Generally, Explore Patterns is most useful when the values are fairly precise, so that matches are less likely to exist through coincidence.

Scientists and engineers are dealing with more and more data streamed from device-based sensors or batch process monitors. Hundreds or thousands of such data streams can create a large volume of data, very quickly, posing a unique set of challenges. No matter what your industry, common difficulties exist with this type of data: simplifying and cleaning up messy data, removing outliers and building models that characterize an underlying function or relate a continuous data stream to measures of performance, such as yield, defect rate or product quality.

JMP Pro 14 introduced FDE, a powerful platform for working with functional data. JMP Pro 15 adds workflow improvements that let users bypass intermediate table creation reshaping, and joins, especially for functional DOEs. The custom designer in JMP Pro 15 allows users to specify a functional response, making the subsequent workflow more convenient and less error-prone. Additionally, with FDE in JMP Pro 15 you can:

• Build a better model in less time with automated knot selection.
• Spend less time table wrangling by using Functional DOEs.

The new Structural Equation Modeling platform in JMP 15 lets you quickly specify, edit, run and compare SEM models using an easy-to-use interface. Structural Equation Modeling is a framework that allows you to specify hypothesized relationships among variables (both observed and unobserved) and test the degree to which these hypotheses seem reasonable, given the data. SEM can be used by anyone who is using standard modeling techniques but needs more control and flexibility in the model specification process.

SEM in JMP Pro 15 is versatile and provides options for modeling simple or multiple regression relationships as well as comparing a set of hypothetical models to decide which model is most reasonable.

With JMP 15, you'll find it easier to build and evaluate models. Multiple contour profilers can be viewed simultaneously. In JMP Pro, the Make Validation Column utility offers more control and an improved interface, and Generalized Regression offers built-in model comparison, improved one-click relaunch options and the ability to change distributions without having to relaunch.

Univariate control charts are unable to account for correlation or functional relationships among multiple parameters. When such relationships exist, standard univariate charts will not accurately depict process health. JMP 15 provides control charts that support these relationships, providing a better understanding of actual process performance. The new Model-Driven Multivariate Control Chart platform in JMP 15 offers several benefits:

• Graphlet-driven drill-downs that allow you to diagnose and monitor processes without having to launch multiple platforms.
• Higher efficiency, as the platform is score-based and does not have to re-compute covariances each time it is run.
• Built-in dimension reduction further improves performance, allowing computations over a lower-dimensional space.
• When driven by PLS, this reduction in dimensionality is tied to the response, so outliers are tied to what is most important.
• Modelers can perform the PLS and hand off the scores to process control engineers so that engineers don’t have to be experts in PLS.

JMP 15 makes it easier for novice scripters to automate their work, allowing them to capture, in a single click, the JSL needed to reproduce common workflows. Also, the new option to copy a table script allows you to capture the table script, without the data itself. Table scripts and all column properties (including formulas) are included.

When you just need to get the JSL for a column (or a few), you can use the new Copy Columns and Paste Columns features in JMP 15. This is especially handy when the columns have properties that require lots of JSL—as value orders, value labels, spec limits, date-time formats and formulas do.

You can also copy Where Clauses, which avoids the need to script complicated conditional row selections (“Where clauses”) and lets you easily capture the JSL needed to make the selection.

In JMP 15, interactive HTML reports have improved support for within-report profilers. Released at the same time as JMP 15, JMP Live is a web-based collaborative analytics platform for JMP. With JMP Live, users can share discoveries using a simple publishing process that fits seamlessly into the JMP analysis workflow. Publish data, dashboards or reports to JMP Live, and have colleagues view the findings—even if they don’t have a JMP license.

• New column header graphs display histograms above each column.
• Import wizard allows import and processing of XML, JSON and .pdf file formats.
• Graph Builder enhancements:
  • New customization options to enhance Heatmap and Box Plot graphs.
  • Improved Contour element with additional options for lines between contours and alpha hull support.
  • Bagplot (or 2D Box Plot) for continuous XY data added to the Contour element.
  • Frequency option in column functions.
  • New Interval > Band option allows band from low value to high value.
  • Time Series Forecast available in Line of Fit graph.
  • New Line of Fit regression line option forRobust Cauchy.
  • Ability to save prediction formula(s) for Line of Fit and save formula for Bar, Points and Line.
  • Upgraded Variability chart and Oneway Axis.
  • Summary statistic property added for Color and Size drop zones in elements that summarize color or size, specifically Points, Line, Bar, Treemap, Heatmap, Box Plot and Contour.
  • More control over the basis for percentages, allowing 100% stacked bars charts without data prep. Now distinguish percent by X, Y or X+Y.
  • New Ridgeline Plots use histogram with a categorical variable for Y.
  • Stacking and fill options added to Line element.

• Recode improvements:
  • New column utility recodes column names.
  • Corresponding cells in the data table are selected when their entries are selected in the Recode dialog box.
  • New option to replace entire string without a regular expression.
  • Ability to apply mapping from another table.
• New Value Order column property allows flexible, customizable sort orders.
• Virtual Join supports multiple links from a single column.
• Local data filters now include a histogram in the column filter control.
• New hover label options extend information available in graphs:
  • Graphlets display a graph created by a JMP platform inside a JMP hover label. These contextual graphs add the ability to further drill down into the data without returning to the data table or launching a new platform.
  • Textlets in hover labels expand options for the appearance of label text.
  • Gridlets in hover labels offer options for formatting numeric values.
• Enhanced Capability Analysis report in Distribution platform (now Process Capability).
• Help menu now navigates to documentation on jmp.com for smaller software installs and more frequent Help updates.
• Support for Dark Mode in macOS.

• HTML5 reports include additional profiler support and connection to JMP Live.

• Publish to JMP Live—the newest member of the JMP product family. JMP Live takes the robust statistics and visualizations in JMP and extends them to a secure online portal—with data filtering and column switchers for interactive collaboration.

• Group Orthogonal Supersaturated Design is a new platform for creating and analyzing supersaturated designs (more factors than runs), having groups of correlated effects. Should confounding persist after the initial analysis, the factors involved are identified and an appropriate augmentation scheme (requiring only a few runs) is advised.

• Instantaneous creation of a globally optimal design when runs are multiple of four and all factors are two-level continuous or categorical.
• Custom Designer provides modeling scripts for Generalized Regression and Fit Mixed. PRO

• Explore Patterns platform investigates data integrity by looking for abnormal features in data including long runs, duplicate long sequences and unusually formatted values.
• Generalized Regression enhancements provide one-click relaunch options and the flexibility of changing distributions without relaunching.
• Enhancements to the Explore Outliers and Explore Missing Values platforms.
• Multiple frame contour profilers can be viewed simultaneously.
• New Model Driven Multivariate Control Chart platform allows users to monitor large amounts of highly correlated processes. The platform can be used in conjunction with the PCA and PLS platforms to monitor multivariate process variation over time, give advanced warnings of process shifts and suggest probable causes of process changes.

• Functional Data Explorer (FDE) has workflow improvements to bypass intermediate table creation, reshaping and joins. This allows functional response DOE, Custom Designer, FDE and Generalized Regression to all work together for a more convenient and robust workflow. PRO
• Improvements to Make Validation Column offer more control and an improved interface. PRO
• Structural Equation Modeling, a flexible new predictive modeling platform, allows you to model relationships among both observed and unobserved (latent) variables. PRO
• Support Vector Machines platform rounds out the JMP Pro modeling toolbox. PRO

• New Copy Columns menu item copies to the clipboard a script to create the column using JSL.
• Table script option, Copy Table Script (No Data), copies the table template without data.
• Scripts generated by operations in the Tables menu can now be saved to the source table.

• Generate JSL for Where clauses via point-and-click.
• Integration with SAS Cloud Analytic Services (CAS) server provides a simpler scripting mechanism, better authentication/authorization control, easier data set retrieval and the ability to run CAS actions from JMP to take advantage of high-performance, large cloud environments built on top of AWS, Azure or OpenStack.

Documentation

Download a .pdf of the new features in JMP and JMP Pro or view our online searchable documentation.

• New Features in JMP 15 (PDF) (in English)
• JMP Online Documentation