A variable selection method for constructing decision trees with rank data is proposed. Itutilizes conditional independence tests based on loglinear models for contingency tables.Compared with other selection methods, our method is computationally more efficient.Moreover, our method is relatively unbiased and powerful in selecting the correct splitvariables. Simulation results and a real data study are given to demonstrate the strength ofour method.
Date:
2012-09
Relation:
Computational Statistics and Data Analysis. 2012 Sep;56(9):2830-2836.
