Chunk #27 — The Methods — How Do Classification and Regression Trees Work? — Splitting and Stopping

Source

An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests.

Embedded

yes

Text

While the principle of impurity reduction is intuitive and has added much to the popularity of classification trees, it can help our statistical understanding to think of impurity reduction as merely one out of many possible means of measuring the strength of the association between the splitting variable and the response. Most modern classification tree algorithms rely on this strategy, and employ the p-values of association tests for variable and cutpoint selection. This approach has additional advantages over the original impurity reduction approach, as outlined below.