Evaluating chi-squared automatic interaction detection

作者:

Highlights:

摘要

We propose a method to compute confidence bounds around the predictions from chi-squared automatic interaction detection (CHAID). These bounds are useful for ex ante target selection as some clusters may or may not overlap. They are also useful for ex post evaluation of the predictive quality of CHAID. The method is illustrated using simulated data.

论文关键词:CHAID,Target selection,Confidence intervals,Bootstrap

论文评审过程:Received 28 May 2004, Revised 28 May 2004, Accepted 8 March 2005, Available online 10 May 2005.

论文官网地址:https://doi.org/10.1016/j.is.2005.03.002