From Q
Jump to navigation Jump to search

CHAID is the name of an algorithm for creating decision trees[1], which uses chi-square tests (this is what the CH in CHAID refers to).

Although Q does not have CHAID, this is only because it uses a more modern approach which takes advantage of advances in computing and statistics since CHAID was developed. See Trees for a description of the approach used in Q and The difference between Trees, CHAID, CART and other tree-based models for a description of the difference between Q's approach, CHAID and related algorithms.

In Q you can use the CHAID algorithm to automatically combine categories in categorical variables. For this, please refer to:



Further reading: Market Segmentation Software

  1. * Kass, Gordon V.; An Exploratory Technique for Investigating Large Quantities of Categorical Data, Applied Statistics, Vol. 29, No. 2 (1980), pp. 119–127