JMP Start Statistics, 5th Edition

Chapter Contents 

Overview

Recursive Partitioning (Decision Trees)

Growing Trees

Exploratory Modeling with Partition

Saving Columns and Formulas

Neural Nets

A Simple Example

Modeling with Neural Networks

Saving Columns

Profiles in Neural

Exercises

Recursive Partitioning (Decision Trees)

The Partition platform recursively partitions a data set in ways similar to carttm, chaidtm, and C4.5. Recursively partitioning data is often taught as a data mining technique, because

• it is good for exploring relationships without having a good prior model.

• it handles large problems easily.

• it works well with nominal variable and messy or unruly data.

• the results are very interpretable.

The factor columns (X’s) can be either continuous or categorical. ...