Data Imputation by Random Forest <BR>- The Principle and Its Application for National Center Test in Japan -

• Ishioka Tsunenori

  The National Center for University Entrance Examinations

Bibliographic Information

Other Title

• Random Forestを用いた欠測データの補完に基づく大学入試センター試験科目間得点差
• Random Forest オ モチイタ ケツソクデータ ノ ホカン ニ モトズク ダイガク ニュウシ センター シケン カモク カン トクテンサ
• Data Imputation by Random Forest-The Principle and Its Application for National Center Test in Japan-

Abstract

Random Forest, one of the ensemble learning methods for classification and non-linear regression model, provides a stable and an accurate data imputation for the missing data. This paper shows that the algorithm works well for a large dataset containing missing data. The examples are science and society examination scores appearing in the Japanese National Center Test in 200x.

Journal

• Ouyou toukeigaku

  Ouyou toukeigaku 40 (3), 193-209, 2011

  Japanese Society of Applied Statistics

Keywords

• imputation
• missing data
• missing at random
• ensemble learning

Details

• CRID: 1390001204442491392
• NII Article ID: 10030153149
• NII Book ID: AN00330942
• DOI: 10.5023/jappstat.40.193
• ISSN: 18838081
• ISSN: 02850370
• NDL BIB ID: 023458127
• Web Site: http://id.ndl.go.jp/bib/023458127
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I023458127
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed