New in JMP® 12

From data import to analysis to sharing results, enhancements in JMP 12 speed the learning cycle and make it easier to reach breakthrough statistical discoveries.

Learn how to get JMP 12

Query Builder

Until now, those who work with databases have often needed to write their own SQL code to join database tables and query them – a tedious and error-prone process requiring a skill set most analysts lack. Query Builder allows users to connect to databases and perform joins and queries using intuitive dialogs. Users unfamiliar with SQL can now get their work done without relying on IT, while advanced SQL programmers can augment the generated code with custom code.

Key Features:

  • Simple interface to create complex ad hoc queries to a database.
  • Foreign keys are automatically linked to primary keys in other tables.
  • Tables and sample results are shown immediately.
  • Filters automatically populate with eligible categories.
  • Sampling.
  • Save query.
  • Prompt for filter values at run time.
  • Examine/edit/save SQL script.

Interactive Model Editing

Supported in many Fit Model personalities, interactive model editing lets you quickly run and compare various models with a drag-and-drop interface within the report. This keeps you in the analysis flow, allowing you to build a model that performs well with fewer clicks, while emphasizing the interactive nature of JMP.

The interactive model editor:
  • Gives you effect summaries – sorted and charted by LogWorth.
  • Lets you select and edit terms without returning to the model launch dialog.
  • Remembers your choices, or lets you undo actions.
  • Included in these Fit Model personalities: Standard least squares, nominal and ordinal logistic, proportional hazards, parametric survival and generalized linear model.

PowerPoint Export

It is always nice to show your data analysis results from JMP directly in JMP. But in some cases, you may need to prepare a slide deck to present your information to others. Now, JMP makes it easy to export your reports as PowerPoint slides. You can reformat slide decks created by JMP with a company template. Tables include editable text, and JMP automatically transfers graph titles to slide titles.

  • Slides are already titled.
  • Tables are imported as editable text.
  • Reports can be imported directly to slides with a company template.

Images in Data Tables

The biggest news for JMP 12 data tables is support for a new data type: Expression. Images can be dragged and dropped into table cells, while lists and matrices can be stored in their “native” forms. The Summary platform can also use this feature to display histograms in the summary table. Graph Builder can export images to a data table. Finally, you can now drag to change row height.

Other ways to use expression columns include:

  • Embedding a JSL expression directly into a row.
  • Nesting matrices and associative arrays into a data table.


Data cleaning/preparation prior to modeling can take up to three times as long as the modeling or analysis itself. Recoding columns that contain character data is often responsible for much of the preparation time. Categorical data is often messy due to misspellings, inconsistent capitalization, abbreviations and structure that require cleaning in preparation for successful modeling.

“Everyone knows that most of the time on a data project is spent cleaning and preparing the data,” says Dick De Veaux, Professor of Statistics at Williams College. “And how many times have you wanted an easier way to group categories that are 'nearly the same'? Now with the Smart Recode tool you can do it automatically."

The new Recode:

  • Makes recoding categorical data – which may have been tedious and error-prone in the past – simple.
  • Includes a string clustering algorithm to group categories together based on character edit distance.
  • Includes many scripting options.
  • Lets you search for categories, and group or filter based on that search.

Graph Builder Additions

Graph Builder was already one of the most-loved tools in JMP. Now it gets a host of new features in JMP 12:

  • Visible landing zones while dragging.
  • Supporting selections in legend.
  • More control of gaps between graph panels.
  • Addition of a graph matrix option.
  • Right-clicking gap now supports color, transparency and size, and the graph borders.
  • New graph types include smoothly connected lines, overlaid histograms, new bar element options for needle and float; support for step, horizontal and vertical modes in line element; and pages role (a pseudo-BY variable).
  • Better support for coloring graphs by various color gradients.
  • Graph Builder launch dialog is available through Script > Relaunch Analysis or with JSL through Graph Builder (Launch Dialog).
  • “Make into Data Table” turns Graph Builder panes into a data table with images.

Interactive HTML Profiler and Bubble Plot

Profiler and Bubble Plot are two of the most popular tools for communicating results with others outside of JMP. Previously, interactive versions of these platforms were available only as Flash, which many devices (especially mobile) cannot play. Now they are available to output as interactive HTML.

Selection Filtering

The Local Data Filter is a powerful visualization aid. Now you can perform the same type of filtering using platforms. Application Builder’s new Data Filter Source Box lets you filter points and output in one area of a report by selecting items from a platform in another area of the report.

DOE Enhancements

JMP software’s world-class DOE features continue to evolve. Definitive screening designs now support blocking, while space-filling designs support categorical factors, the Augment feature, and a new criterion for optimizing these designs, MaxPro. Split plots can now work with covariate factors, and a Data Filter-like interface now allows disallowed combinations to be specified via drag and drop.

Multiple Correspondence Analysis

Multiple Correspondence Analysis is a data analysis technique that’s similar to principal component analysis, but for categorical data. It helps to visualize and uncover hidden structures in a data set consisting of more than two categorical columns. Such information is useful in market research to identify target audiences for advertisements.

Process Capability

Enjoy a unified platform for assessing process capability. JMP reports within (short-term) capability and overall (long-term) capability. You can subgroup a process by nesting the column in a categorical variable, or set a constant subgroup size for a process. The graphics are updated, and you see both CPK and PPK by default. Finally, it’s extremely easy to import and export spec limits. You can also run a capability report directly from Control Chart Builder.

Destructive Degradation

To measure a product characteristic, sometimes the product must be destroyed. For example, when measuring breaking strength, the product is stressed until it breaks. The new Destructive Degradation platform for reliability studies handles this type of analysis and has a built-in model library with visual representations of many standard models, transformations and data distributions. Includes a model comparison, CDF and Quantile Profilers.

“We are treated to an array of new features with each new version of JMP,” says William Q. Meeker, Professor of Statistics at Iowa State University. “I am particularly impressed by the new destructive degradation platform. With the slick interface, analysis of destructive degradation data will be remarkably simple, allowing useful inferences on both degradation metrics and failure-time metrics. As usual, the JMP developers have made effective use of the ubiquitous and powerful JMP Profiler.”

Clustering Improvements

An updated Cluster platform helps address common issues in data preparation prior to clustering. This includes reporting, data manipulation, dimension reduction and summarization.

The Cluster platform better addresses these common analysis issues:

  • Reporting: To characterize clusters, you can now see a summary and a graph of your clusters in one step.
  • Data manipulation: Data often needs reshaping prior to clustering. The platform can access data in four different forms: stacked, summarized, distance matrix and data as usual; processes raw data in-line with the analysis, saving many steps in the process.
  • Dimensionality: In the semiconductor and other industries, it is important to determine clusters of wafer defect patterns. This previously meant creating one variable to make XY coordinates, then splitting on this dimension, clustering, and merging the clusters. Now, JMP accomplishes this in one step.
  • Summarization: More easily cluster summarized data.
  • Scoring: Use a scoring formula to classify new data into clusters.

Discriminant Analysis Improvements

The updated Discriminant platform includes a number of new features, making it a more useful tool in a predictive modeler’s toolbox, especially with larger problems.

New features include:

• Linear Wide, a new method for wide data cases. Useful when the covariance matrix is too big to calculate (thousands of variables).

• Make Scoring Script lets you create a script that has the same effect as the Save command if you run it, but a script can be applied to a separate data table.

Modeling Utilities

A number of utilities help prepare data sets for analysis automatically, making data preparation more efficient – where you spend most data analysis time.

Modeling utilities in JMP 12 include:

  • Explore Outliers: Find outliers using numerous methods, including quantile- based outliers, multivariate robust outliers, K-nearest neighbors or robust estimates. After this, select, color cells and/or rows, exclude, add to missing value codes or change missing.
  • Explore Missing Values: Run a missing value report, cluster row and column missingness, view a graphical pattern of missing values and perform imputations using multivariate normal or multivariate SVD.
  • Screen Predictors: “Tree-shaking” method that performs exploratory variable reduction to reduce dimensionality in follow-up modeling tasks.

JMP® 12 New Features Overview

Data Import, Cleanup and Cleansing
  • Query Builder helps you discover interesting data and make correct queries that are repeatable and sharable. Build custom prompts, sample databases and monitor queries in progress.
  • Recode now lets you clean up messy data with a suite of powerful tools, including string clustering based on character edit distance. Recode manually, automatically, with a script or using a combination of these.
  • Anonymize, a data table utility, disguises column names and data values while maintaining data structure.
  • The Cols menu has a new Utilities submenu, which includes Recode, Compress Selected Columns, Text to Columns, Combine Columns, Make Binning Formula and Make Indicator Columns.
  • The Cols menu has a new Modeling Utilities submenu, which includes Explore Outliers, Explore Missing Values and Screen Predictors.
  • Support for more than 231 rows in a data table. Support for 64-bit integers.
  • File previewer for Mac version of JMP and Quick Look preview plugin for Mac OSX now available.
  • Excel Import Wizard now available on Mac version of JMP.
  • Option to close all or multiple windows on Mac version of JMP now available.

Design of Experiments
  • Disallowed Combinations Filter available in DOE platforms.
  • Definitive screening designs support blocking.
  • Space-filling designs support categorical factors.
  • New MaxPro criterion allows space-filling designs to reach design boundaries.

Statistics, Predictive Modeling and Data Mining
  • Visual model editor lets you quickly run and compare various models with a drag-and-drop interface.
  • Clustering improvements reduce pre-processing time. The platform now supports stacked data, includes summary features and lets you focus on just a column cluster of interest.
  • The Discriminant platform includes many new capabilities, such as robust fitting options, support for missing data, canonical variables centering, increased dimensional support and improved scoring functions.
  • X11 decomposition available in Time Series platform.
  • ANOR (analysis of ranges), which provides information about group variation, now included in Analysis of Means methods.
  • PCA supports wide principal components analysis.
  • Cauchy fitting now available in the Response Screening platform.

Data Visualization and Exploratory Data Analysis
  • Export JMP reports directly to Microsoft PowerPoint with a single click, making it easier to build presentations of your analysis.
  • New Expression data type in data tables supports matrices, associative arrays, JSL expressions and images.
  • Graph Builder enhancements include visible landing zones while dragging; selectable legends; more control over graph formatting; overlaid histograms; needle and float bar types; step, horizontal, vertical and spline-based line elements; pages role (a pseudo-BY variable).
  • A launch dialog box is now available for Graph Builder, providing for true BY groups and improved performance when analyzing large data sets.
  • “Make into Data Table” command in Graph Builder exports graphs into expression columns.
  • Axis settings dialog box has many interface updates and new features, including multilevel axis property modifications for nested axes, axis reference ranges and categorical tick marks that match up with the underlying numeric values.
  • Legends are selectable in many platforms.
  • Interactive HTML output available for Bubble Plot and Profiler.
  • New tiling algorithm in Treemap draws rectangles in order of size while keeping rectangles as close to square as possible.
  • Ternary Plot and Mixture Profiler have improved behavior for the magnifier and hand tools, and they support editing of Axis properties, including minimum/maximum, major and minor gridlines, and reference lines.
  • New transforms include selected rows transform, abbreviated month and distributional transforms (center, standardize, range 0 to 1, Box Cox, Johnson normalizing, informative missing).
  • Summary supports Histogram option, which saves an image of a histogram to the summary table for each group as an expression column.
  • Create a new formula column for popular transforms by right-clicking a column in the data table.

Consumer and Market Research
  • Multiple Correspondence Analysis (MCA), which is like principal components analysis for categorical factors, has been added. MCA is useful when a data set has more than two categorical columns or contains multiple response data.
  • Categorical platform improvements include Likert plots and the binomial rate test (an alternative to the default homogeneity test for multiple response data).
  • Choice models include two new Profilers: Multiple Choice and Probability.

Quality Engineering, Reliability and Six Sigma
  • New Destructive Degradation platform enables you to choose from several model path definitions, transformations and failure distributions. Platform includes a model comparison report, and CDF and Quantile Profilers.
  • Reliability platforms have a consolidated censor code widget.
  • Compare groups in Life Distribution by overlaying multiple groups on the same plot.
  • Overlay likelihood contour on top of the prior and post scatterplot in Life Distribution.
  • Row-based storage and import of spec limits now supported.
  • Numerous enhancements to Reliability Forecast platform include allowing different costs for different groups and support for Defective Subpopulation distributions.
  • Attribute charts in Control Chart Builder now support noninteger data.
  • Define specs within, and generate capability reports directly from, Control Chart Builder.
  • New unified Process Capability platform reports both within (short-term) and overall (long-term) capability.
  • Fit Mixture and Fit Competing Risk Mixture added to Life Distribution platform.
  • One-sided or two-sided option for custom estimation is now available in Life Distribution.

Analytical Application Development
  • Selection filtering enables one graph to filter another (accessible through AppBuilder and JMP Scripting Language).
  • Surround a subexpression by the function As Constant(); to evaluate the expression only once, speeding up scripts that have complex but constant expressions.
  • AppBuilder allows you to arrange more than one module in a single window and to edit applications embedded in data tables.
  • Display and edit box properties are easier to adjust and customize.
  • Internet Open(); now creates a script to import images if they are available in an HTML table.


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

Back to Top