This course is for JMP users who need to build descriptive and predictive models between sets of multidimensional data. The course demonstrates various ways of performing supervised learning where the relationships among both the output variables and the input variables are considered in building these models. Strong emphasis is on understanding the results of the analysis and presenting your conclusions with graphs.

Learn how to

• classify observations into groups with discriminant analysis
• Build more stable models by removing collinearity with principal components regression (PCR)
• fit complex multivariate predictive models with partial least squares (PLS) regression models.

Who should attend

Individuals who work with high dimensional data and have a need to build models to predict response outcome(s) or group assignments

Formats available	Standard duration
Classroom:	1.0 day

Before attending this course, you should complete the JMP Software: Statistical Decisions Using ANOVA and Regression course. Completing the JMP Software: Analyzing Multidimensional Data course would be helpful, but it is not necessary.

This course addresses JMP software.

Introduction to Multivariate Data

• examples of supervised learning
• review of matrix algebra

Discriminant Analysis

• geometry of discrimination
• linear and quadratic discrimination
• variable selection
• validation
• classification

Principal Components Regression

• review of principal components
• principal component regression
• variable selection

Partial Least Squares Regression

• PLS algorithms
• PLS regression