Data Selection and Management
Data Visualization and
Exploratory Data Analysis with JMP®
In JMP, data visualization and exploratory data analysis (EDA) go hand in hand, giving you the tools you need to make breakthrough discoveries and communicate results. Linking dynamic graphics with powerful statistics, JMP helps you construct a narrative and interactively share findings in ways colleagues and decision makers can readily understand and act upon.
With JMP, analyses unfold, driven by what the data reveals at each step. You can explore your data without leaving the analysis flow or having to rerun commands as new questions arise. And the in-memory architecture of JMP means you don’t have to wait for a server to return data analysis results, even with significant volumes of data.
JMP supports heuristic, open-ended and dynamic EDA, which often involves significant data quality and aggregation steps as users analyze data and try different visualizations to tell its story most accurately. EDA is a data analysis tool that can also guide you in building a useful model.
Data Selection and Management
Collection and modification of data are the first and most important steps of your analytic journey – and often the most time-consuming. Exploratory data analysis (EDA) helps find structure in data – whether in small samples or large volumes of data collected from many domains. JMP offers the tools you’ll need to expedite this vital portion of the analysis workflow, with a rich suite of tools to access, combine, filter and cleanse your data in preparation for data analysis. The interactive graphics and robust data analysis capabilities in JMP make it an ideal alternative to Excel for EDA and other types of statistical data analysis.
Linked Interactive Graphs and Analysis
The heart of JMP visuals are interactive graphs, supported by world-class analytics. Dynamic linking allows selections made on one graph or data table to be reflected in all graphs that are based on that table. The ability to view multiple graphs displaying the same selected data is one of the distinctive architectural underpinnings of JMP, which allows you to explore the data and build on the analysis in multiple ways.
Perception is personal, and the open-ended nature of EDA means that you will develop your own style of analysis. JMP provides a wide repertoire of best-practice visualizations as part of the analysis output, so there are few limitations. Various tools allow you to pan and probe these displays, zooming in for a closer look. The innovative Graph Builder lets you interactively build displays with multiple X and Y grouping variables incorporating several types of graphs, including bar charts, histograms, line charts and contour plots. Even with high-dimensional data, you can find ways to see structure. Added insight often comes from using multiple visualizations simultaneously, and dynamic linking and data filter capabilities in JMP make this approach especially useful. You can also use graphs to filter other graphs.
To show data geospatially, you must merge it with map views at any level of granularity. JMP includes prebuilt maps for countries, states and other regions. In addition, you can get even more granular by entering specific map details using a free JMP add-in that lets you quickly define the X and Y coordinates to match your data. This allows data to be merged with geospatial maps at any level of detail required.
JMP even lets you plot your data on street-level maps, giving you access to geographic features such as cities, roads or bodies of water. These additional details give geospatial context to your data, providing you with additional insights that would otherwise be difficult or impossible to unearth. These detailed graphs can also be compelling communication tools when sharing your discoveries.
SAS servers host map data that create the images from open source maps available from OpenStreetMap (OSM). These servers can generate and return the maps when you select Street Map Service from any platform in JMP that supports background maps.
The purpose of your analysis is not just to create impressive graphs and statistics, but to help drive decisions. Whether it’s showing the distribution of input variables that impact outcomes you are trying to predict, or graphically displaying the relationships in those variables through the interactive Profiler, visualizations can communicate significant effects. By integrating interactive graphs with supporting analytics, JMP gives you the tools you need to make informative, compelling presentations of your results.
JMP Graph Builder is the best way to view and explore JMP data tables right on your iPad. Create, edit and view graphs wherever you are with the same Graph Builder engine found in JMP, the desktop statistical discovery software from SAS. Data Filter lets you focus in on specific parts of the data that you are graphing. Consider this free iPad app a bonus for choosing JMP for your statistical discovery needs.
Interactive HTML enables JMP users to share dynamic graphs and reports, so that even those who don’t have JMP can explore the data. The JMP report is saved as a Web page in HTML5 format, which can be e-mailed to users or published on a website. Users then explore the data as they would in JMP. The report can be viewed on any device with a browser, including most mobile devices.
Interactive HTML provides a subset of features from JMP:
- Explore interactive graph features.
- View data by brushing.
- Show or hide report sections.
JMP also gives you the ability to export reports into PowerPoint with a single click.
Excel and JMP Together
Want to leverage your collection of spreadsheets? You can use your Microsoft Excel spreadsheets to conduct what-if analyses and analyze potential outcomes. The JMP Add-in for Excel adds a layer of ease and sophistication. It manages the importation of data from your spreadsheets into JMP, adds more analytical power for what-if analysis, and performs Monte Carlo simulation to predict potential outcomes based on your targets.