Variable Selection for Classification Trees with Ordinal Responses
碩士 === 國立中正大學 === 數理統計研究所 === 99 === For ordinal responses, we propose a variable selection method for classification trees. The selection scheme is proposed to control bias by testing independence between response and predictor where loglinear model for two-way contingency table is fitted to the da...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2011
|
Online Access: | http://ndltd.ncl.edu.tw/handle/93682360984205376534 |
Summary: | 碩士 === 國立中正大學 === 數理統計研究所 === 99 === For ordinal responses, we propose a variable selection method
for classification trees. The selection scheme is proposed to control
bias by testing independence between response and predictor where
loglinear model for two-way contingency table is fitted to the data.
We find that our method is relatively unbiased and more powerful
than the selection method proposed by Piccarreta (2008).
|
---|