Chi-square automatic interaction detection: Difference between revisions

Revision as of 13:33, 7 September 2009

Revision as of 13:35, 7 September 2009

Line 1:

'''CHAID''' is a type of [[decision tree]] technique, based upon adjusted significance testing. It was published in 1980 by Gordon V. Kass. It can be used for prediction (like [[regression analysis]], originally known as XAID) or for detection of interaction between variables. CHAID stands for '''CH'''i-squared '''A'''utomatic '''I'''nteraction '''D'''etector, based upon a formal extension of the AID (Automatic Interaction DetectionDetector) and THAID (THeta Automatic Interaction DetectionDetector) procedures of the 1960's and 70's.

In practice, it is often used in the context of [[direct marketing]] to select groups of consumers and predict how their responses to some variables affect other variables.

Line 23:

*[http://www.statsoft.com/textbook/stchaid.html Statsoft - CHAID Analysis]

*[http://www.jmp.com/software/whitepapers/partition_platform/index.shtml JMP Partition Platform]

*[http://www.xlstat.com/en/features/trees.htm - CHAID in XLSTAT]

*[http://www.spss.com/answertree/decisiontrees.htm SPSS - How decision tree results are different in AnswerTree]

*[http://www.smartdrill.com/About/process4.html SmartDrill - Analytic Techniques: CHAID]