ERIC Number: ED064362
Record Type: Non-Journal
Publication Date: N/A
Pages: 10
Abstractor: N/A
ISBN: N/A
ISSN: N/A
EISSN: N/A
Multiple Regression Analysis and Automatic Interaction Detection.
Koplyay, Janos B.
The Automatic Interaction Detector (AID) is discussed as to its usefulness in multiple regression analysis. The algorithm of AID-4 is a reversal of the model building process; it starts with the ultimate restricted model, namely, the whole group as a unit. By a unique splitting process maximizing the between sum of squares for the categories of each variable while minimizing the error sum of squares (within group sum of squares), AID-4 seeks out that variable which has the largest between sum of squares and splits the original group into two mutually exclusive groups on this variable at that category where the maximum between sum of squares occurred. The major advantage of using AID-4 is that the maximum squared composite correlation is obtained without the task of attempting to identify the various relevant combinations of linear and non-linear interaction terms by trial and error necessary in the full model of the multiple regression technique. (Author/DB)
Publication Type: N/A
Education Level: N/A
Audience: N/A
Language: N/A
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A