PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
January 1, 1980Journal of the Royal Statistical Society Series C (Applied Statistics)2,895 citations

An Exploratory Technique for Investigating Large Quantities of Categorical Data

View Full Paper
GKGordon V. Kass

Key Points

  • The aim is to introduce and describe a new technique, CHAID, tailored for analyzing categorical data.
  • Describes modifications to the AID (Automatic Interaction Detection) method.
  • Introduces built-in significance testing to prioritize the most significant predictors.
  • Explains multi-way splits and a new predictor for handling missing information.
  • CHAID allows for more robust analysis of categorical data than traditional AID.
  • Enables inclusion of significant predictors through improved testing methods.
  • Facilitates data analysis with a focus on handling incomplete data more effectively.

Abstract

SUMMARY The technique set out in the paper, CHAID, is an offshoot of AID (Automatic Interaction Detection) designed for a categorized dependent variable. Some important modifications which are relevant to standard AID include: built-in significance testing with the consequence of using the most significant predictor (rather than the most explanatory), multi-way splits (in contrast to binary) and a new type of predictor which is especially useful in handling missing information.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Gordon V. Kass (1980) studied this question.

synapsesocial.com/papers/69d72932ef370a38abf511bchttps://doi.org/10.2307/2986296
Ask AI
Helpful
Bookmark
Share
View Full Paper