Chunk #41 — The Methods — How Do Classification and Regression Trees Work? — Prediction and Interpretation of Classification and Regression Trees

Source

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

Embedded

yes

Text

The term “interaction” commonly describes the fact that the effect of one predictor variable, in our example alcohol_per_month, on the response depends on the value of another predictor variables, in our example friends_smoke. For classification trees this means that, if in one branch created by friends_smoke it is not necessary to split in alcohol_per_month, while in the other branch created by friends_smoke it is necessary, as in Figure 1 (left), an interaction between friends_smoke and alcohol_per_month is present.