%0 Journal Article
%T Model-Free Feature Screening Based on Gini Impurity for Ultrahigh-Dimensional Multiclass Classification
%A Zhongzheng Wang
%A Guangming Deng
%J Open Journal of Statistics
%P 711-732
%@ 2161-7198
%D 2022
%I Scientific Research Publishing
%R 10.4236/ojs.2022.125042
%X It is quite common that both categorical and continuous covariates appear
in the data. But, most feature screening methods for ultrahigh-dimensional clas</span><span style=\"font-family:Verdana;\">sification assume the covariates are continuous.
And applicable feature screening</span><span style=\"font-family:Verdana;\"> method is very limited</span></span></span><span style=\"font-family:Verdana;\"><span style=\"font-family:Verdana;\"><span style=\"font-family: Verdana;\" capt\",serif;\"=\"\" pro=\"\" minion=\"\">;</span></span></span><span><span><span style=\"font-family:\" capt\",serif;\"=\"\" pro=\"\" minion=\"\"><span style=\"font-family:Verdana;\"> to
handle this non-trivial situation, we propose a </span><span style=\"font-family:Verdana;\">model-free feature screening for ultrahigh-dimensional
multi-classification with both categorical and continuous covariates. </span><span style=\"font-family:Verdana;\">The
proposed feature screening method will be based on Gini impurity to evaluate
the prediction power of covariates. Under certain regularity conditions, it is
proved that the proposed screening procedure possesses the sure screening
property and ranking consistency properties. We demonstrate the finite sample
performance of the proposed procedure by simulation studies and illustrate
using real data analysis.
%K Ultrahigh-Dimensional
%K Feature Screening
%K Model-Free
%K Gini Impurity
%K Multiclass Classification
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=120753