Statistical Modeling and Predictive Analytics in JMP®
Building useful statistical models is part science and part art, whether your models need to describe and/or predict, and whether they are simple or complex – for example, with random effects, nonlinearity, unusual data characteristics or other challenges.
The analytics in JMP help reveal relationships among variables in a process, enabling you to not only make predictions, but also to identify settings for factors that yield optimal performance.
Through its visual and interactive graphics, JMP helps you communicate results to people who might not create statistical models themselves, but who need to make better-informed, data-driven decisions. Whether your statistical model is deterministic, or involves necessary noise as well as a signal, JMP is equipped to handle your modeling needs. If your objective involves prediction rather than just exploration, JMP Pro, which includes capabilities for advanced analytics users, also makes it easy for you to ensure that predictions will generalize well.
In modeling situations where one or more responses are of interest, the Profiler in JMP allows you to interactively review and optimize these outcomes, and compare and contrast different statistical models of the same type or of different types. This innovative method for visualizing models lets you easily explore trade-offs when you need to optimize multiple responses – plus it helps you share your statistical analysis with others, so you can drive deeper understanding and greater insight throughout your organization.
- Categorical Platform
- Fit Y by X
- Time Series
The Categorical platform in JMP provides tables, summaries and statistical tests of response data and multiple response data when the measured responses indicate membership of a particular category. Such data is generated in a variety of settings, including measuring test results, classifying defects or side effects, and administering surveys. Partly because of its diverse application, categorical data can be presented in a variety of formats. A particular strength of the Categorical platform is that it can handle this diversity without any need to reshape the data prior to exploration and analysis. One or more columns can be used to define the categories within and between which variation in the response is assessed, and the Categorical report contains the resulting charts of share and frequency, by category. Used in conjunction with the Data Filter, these charts provide for quick and easy review of large-scale survey data. The report can also display the associated tabulations and cross tabulations, which can be quickly transposed for easier viewing or printing if needed. Depending on the nature of the responses, you can statistically address questions like: Does the pattern of response vary with sample categories, and have they changed over time? For each response category, are the rates the same across sample categories? How closely do the raters agree? What is the relative risk of different treatments?
When your spreadsheet can’t perform the statistical analysis you need or you have so much data that you can’t easily see what it contains, the JMP Add-In for Microsoft Excel allows you to dig deeper.
In many ways, JMP software’s innovative Fit Y by X platform is an application in its own right. As the name implies, it allows you to test for and model dependencies between a single input and a single response or outcome. By using pre-assigned statistical modeling types, Fit Y by X is able to unify what is normally considered to be a disparate set of statistical approaches into a coherent, understandable whole.
Time series analysis in JMP allows you to explore, model and forecast univariate time series. Your statistical modeling approach can be informed by the usual diagnostics, including plots of autocorrelations and partial autocorrelations, variograms, AR coefficients and spectral density plots.
The Partition platform in JMP enables you to find cuts or groupings of inputs (Xs) that can best predict the variation in an output (Y). This process of splitting the data is recursive – you continue it until you get a useful fit. Grow your tree using decision trees, bootstrap forests (JMP Pro only) or boosted trees (JMP Pro only).
The Neural platform in JMP Pro enables you to build fully connected neural networks with hidden nodes in one or two layers. Each node can have one of three different activation functions, and you can have any number of nodes in each layer. Use boosting to help your network to learn difficult cases, and specify one of four penalty methods for your fit.
A key technique in unsupervised learning, clustering forms subgroups so that cases in a particular subgroup are more alike than those in another subgroup. The Cluster platform in JMP lets you scale and transform variables before analysis, and includes interactive hierarchical and K-means clustering.
- Selected JMP capabilities in Modeling and Predictive Analytics
More resources for Modeling and Predictive Analytics
Customer Success Stories
More on Modeling
Contact JMP Sales