ASCAID: using an asymmetric correlation measure for automatic interaction detection. (English) Zbl 05280202

Hilbert, Andreas

Schader, Martin (ed.) et al., Between data science and applied data analysis. Proceedings of the 26th annual conference of the Gesellschaft für Klassifikation e. V., Mannheim, Germany, July 22–24, 2002. Berlin: Springer. Stud. Classification Data Anal. Knowl. Organ., 447-455 (2003).

Summary: Based upon the predictive association measure \(\lambda\) by Goodman and Kruskal, a new algorithm for the induction of a decision tree is proposed. This algorithm cares about the asymmetric character of the classification task and enables the use of statistical inference.
For the entire collection see [Zbl 1023.00021].

MSC:

62-XX

Statistics

Software:

ASCAID