While SAS has not officially announced JMP 19 as of this writing, the roadmap likely includes:

JMP (Jump) is a popular statistical discovery software package developed by SAS Institute. Here is a brief overview of the major version releases:

JMP 11 leaned heavily into the formulation industry (food, chemicals, cosmetics) and predictive analytics.

Highlights:

In the beginning, there was the mainframe. Data lived in cold, blinking rooms, and to speak with it, you had to learn the ancient tongues of SAS, Fortran, or JCL. Graphics were an afterthought, a line of asterisks printed on green-bar paper.

Then, in 1989, a whisper came from a Macintosh lab in Cary, North Carolina. Two SAS Institute co-founders, John Sall and James Goodnight, had a radical vision: what if you could see the statistics?

Version 1.0 (1989): The First Click

JMP 1.0 was born not as a command-line titan, but as a Macintosh prodigy. Its name, “John’s Macintosh Project,” was a humble disguise for a revolution. With a mouse click, you could draw a scatterplot. With a drag, you could rotate a 3D cloud of data points. Statisticians scoffed at first—"Real analysis isn't played with toys." But the first users felt magic. The “Linked Brushing” feature was a miracle: click a point in a graph, and it would highlight in every other graph simultaneously. For the first time, outliers screamed for attention, and patterns danced in color. It was slow, it was limited to 32,000 rows, but it was alive.

Version 3 (1995): The Cross-Platform Leap

For years, JMP remained a Macintosh jewel. But the world was turning beige and boxy with Windows 95. JMP 3 bridged the schism. It ran on both, a statistical diplomat. This version introduced the "JMP Journal"—a living notebook that could embed graphs, results, and your own notes into a single, interactive document. No more copying and pasting into Word; the analysis was the report. Scientists and engineers, tired of the PC vs. Mac wars, finally had a common ground to explore their factorial designs and response surface maps.

Version 4 (2002): The Language of Automation

The point-and-click explorers had become powerful, but they yearned for speed. JMP 4 answered with a secret: JMP Scripting Language (JSL). At first, it felt like a hidden rune—cryptic, powerful, and dangerous in the wrong hands. A quality engineer at a semiconductor fab wrote her first script to automate a 50-step DOE analysis. What took a morning now took a minute. JMP transformed from a tool into a platform. Users weren't just analyzing data; they were building systems to analyze data.

Version 5 (2005): The Visual Scientist

The early 2000s brought data deluge. JMP 5 introduced "Graph Builder"—a revolutionary drag-and-drop canvas. You could throw columns onto axes, color, size, and group variables, and the graph would rebuild instantly, as if reading your mind. This was the era of "Visual Six Sigma." A manufacturing plant could now watch a live dashboard of torque readings and instantly fit a Weibull distribution to predict failure. The black belts wielded JMP like a lightsaber, cutting through variation.

Version 9 (2010): The Interrogation Suite

With version 9, JMP grew teeth. It added a dedicated "Time Series" platform and a "Control Chart Builder" that made SPC not just rigorous, but beautiful. But the true gem was "Fit Y by X"—a single launch window that could decide if you needed a t-test, ANOVA, logistic regression, or contingency table, just by looking at the data types you gave it. It was no longer a tool you had to instruct; it was a tool you could converse with.

Version 11 (2014): The Excel Killer

Data never arrives clean. It arrives in Excel spreadsheets with merged headers, missing values, and a hundred worksheets named "Final_v2." JMP 11 introduced the "JMP Data Table" and a vastly improved "Import Wizard" that could tame the wildest CSV or Excel file. It also gave us "Column Switcher"—allowing you to swap variables in a dashboard and watch all graphs update in real time. Marketing analysts wept with joy.

Version 14 (2018): The Engineer’s Engine

The modern era demanded precision. JMP 14 unveiled a stunning "Reliability and Survival" platform, complete with a "Degradation" analyzer that could predict when a lightbulb would fail, a battery would die, or a bridge would crack—before it happened. The "Functional Data Explorer" allowed you to treat entire curves (like temperature profiles across a day) as single data points. It was a leap from static numbers to dynamic shapes.

Version 17 (2022): The Bridge to the Future

As data grew too vast for memory, JMP 17 became a master of connection. It could query databases live, connect to Python, and run SAS code natively. The "New Formula Engine" calculated at blistering speeds. And the "Predictive Modeling" menu—packed with random forests, neural nets, and boosted trees—was no longer a specialist's toy. It was a drop-down menu for everyone.

The Present (Version 18, 2023): The Living Document

Today, JMP 18 is not a program. It is a place. Reports are live. Graphs breathe. When you change a filter, a dozen analyses recalculate behind the scenes without a single click of a "Run" button. The JMP Journal is now a complete narrative—a story of data, from the first messy import to the final, validated prediction.

And if you listen closely at startup, you can still hear the ghost of 1989: the quiet click of a mouse, the rotation of a 3D scatterplot, and the voice of John Sall whispering, "See what your data is trying to tell you."

JMP statistical software has evolved from a niche Macintosh tool into a comprehensive data analysis platform for Windows and Mac. Originally standing for " John’s Macintosh Project ," it was first released in October 1989.

Below is a chronological overview of JMP version history based on major release highlights:

JMP (Statistical Discovery Software) has evolved from a niche Macintosh tool in 1989 into a robust multi-platform analytics suite

. Below is the detailed version history and significant milestones. Wiley Interdisciplinary Reviews Early Foundation (1989–1999) Version 1 (1989):

Launched in October for Apple Macintosh, focusing on graphical interactivity and linking statistics with visual data. Version 3.2.2 (1995): First release to support the Windows operating system. Version 4 (2000):

Introduced more flexible graph modification options and improved data journaling features. Wiley Interdisciplinary Reviews Expansion & Integration (2002–2010) Version 5 (2005): Added advanced data mining tools like Decision Trees Neural Nets . This version also briefly supported Linux. Version 7 (2007): Began a deep integration with

, allowing users to write SAS code and retrieve server data directly within JMP. It also introduced bubble plots. Version 8 (2009): 64-bit support for macOS and a drag-and-drop interface for graph building. Version 9 (2010): Integrated with the R programming language

and added a dedicated Excel add-in. The main interface was rebuilt, and the Degradation platform was launched. Modern Analytics Era (2015–2022) Version 12 (2015):

Focused on reproducibility with enhanced release notes and JSL compatibility. Version 14 & 15:

Introduced modern data visualization and streamlined modeling workflows. Version 17 (2022): Key features included the Workflow Builder for point-and-click automation, (Design of Experiments), and Sample Size Explorers. JMP User Community Current Generations (2024–Present) Release Notes for JMP 18.1.1

JMP (John's Macintosh Project) was first released in JMP Statistical Discovery LLC

(a subsidiary of SAS). Originally designed to leverage the graphical interface of the Apple Macintosh, it has evolved into a powerhouse for interactive data exploration across both Windows and macOS. JMP Statistical Discovery Key Version Milestones

The evolution of JMP is marked by major shifts in data handling and scripting capabilities: JMP 1 (1989):

The original release, focused on linking statistics with Macintosh graphics for scientists and engineers. JMP 2 (1991): Doubled in size and introduced interactive graphics. JMP 3.1 (1994): First version to support Microsoft Windows JMP 4 (2002): A major rewrite that introduced JMP Scripting Language (JSL) and ARIMA modeling. JMP 17 (2022): Introduced

, an end-to-end platform to simplify the Design of Experiments process. JMP 18 (2024): Refined Easy DOE and improved the overall user interface. JMP 19 (2025):

The current major release (Oct 2025), featuring expanded automation, updated One-Page Guides , and a specialized Student Edition. JMP Statistical Discovery Version Feature Comparison JMP documentation

JMP was first launched in 1989 as a product of SAS Institute. Over the decades, it has evolved from a Macintosh-only statistical tool into a multi-platform suite used for complex data exploration and predictive modeling. 🏛️ Origins and Early Growth

1989 (Version 1): Launched by SAS co-founder John Sall to provide a visual, interactive way to explore data on the Apple Macintosh.

Version 3.1.5: An early 1990s release that ran on "Classic" Mac OS (System 9).

Version 4: Introduced the JMP Scripting Language (JSL), allowing users to automate analysis and build custom applications. 🚀 Major Modern Milestones How to open data files from earlier versions?

JMP (pronounced "jump") is a statistical software suite developed by the SAS Institute. It was designed for interactive, visual, and exploratory data analysis.

The history of JMP is not just a story of software updates; it is a history of shifting paradigms in data science. From John Sall’s Macintosh vision in 1989 to the modern AI-assisted JMP 18, the software has consistently prioritized visual discovery over syntax memorization.

Today, JMP is used everywhere from NASA (for rocket engine test data) to Procter & Gamble (for detergent formulation) to the Mayo Clinic (for clinical trial analysis). As data grows larger and models grow more complex, JMP’s unique value remains unchanged: a tool that lets you see what the data are trying to say.

Whether you are a die-hard fan of JMP 4.0 still running on Windows XP or a data scientist using JMP Pro 18 with Python, one thing is certain: the jump through version history is far from over.

JMP 10.0 (2012) focused on in-memory performance and added Formula Depot for reusable calculations. The Query Builder allowed SQL access without leaving the interface.

JMP 11.0 (2013) made a bold move: Multiple file import (drag and drop dozens of CSVs) and Interactive HTML5 output—graphs that remained dynamic in a web browser. This was rare at the time.

JMP 12.0 (2015) brought Recode (a visual column recoding tool) and DOE enhancements like definitive screening designs. The Pro version added boosted trees and cross-validation for serious modelers.

Verdict: JMP was now handling millions of rows effortlessly and outputting reports that non-users could explore. Big data-friendly, yet still point-and-click.

JMP 14 (2018) JMP 14 focused on the user experience of sharing. It improved HTML5 output, meaning interactive graphs could be shared with colleagues who didn't have JMP installed. It also introduced more "one-click" analysis features, reducing the friction between importing data and finding insights.

JMP 15 (2019) Collaboration was the keyword. JMP 15 introduced the ability to save and share "JMP Public" files easily, fostering a community of shared data. It also introduced updates to the Text Explorer, making unstructured text analysis (like customer feedback forms) accessible to non-linguists.

JMP 16 (2021) JMP 16 brought a modernized user interface, including a dark mode (finally!). It focused on mixed models and robust outlier detection. The integration with Python was also significantly improved, acknowledging that modern data scientists work in multiple languages.

JMP 17 (2022) This version leaned heavily into the lifecycle of data analysis. It introduced features for better reproducibility and reporting. The platform stability was enhanced, and the connection to JMP Live—a platform for sharing interactive reports within organizations—was strengthened.

JMP 18 (2024) The latest major iteration continues the trend of integration and AI assistance. With a focus on "Auto-recode" for cleaning messy data and enhanced AI/ML platforms, JMP 18 ensures that while the software remains rooted in statistics, it is ready for the future of automated analytics.