An Estimation Procedure for Contingency Table Models Based on Nested Geometry

• Hirose Yoshihiro

  Department of Mathematical Informatics, Graduate School of Information Science and Technology, the University of Tokyo

• Komaki Fumiyasu

  Department of Mathematical Informatics, Graduate School of Information Science and Technology, the University of Tokyo RIKEN Brain Science Institute

Abstract

We propose a method for estimating the parameters of contingency table models, which is motivated by a geometrical idea. Our method—bisector regression for contingency tables (BRCT)—is based on a nested structure of contingency table models. Our method estimates parameters corresponding to the interactions of lower orders after estimating or eliminating those of higher orders. BRCT generates a sequence of parameter estimates, each element of which represents a model and a parameter estimate. The length of the sequence is equal to the number of parameters, which is much smaller than the total number of models. We describe the BRCT algorithm and show an example. We provide explanations for two cases: (a) two factors and (b) K factors.

Journal

• JOURNAL OF THE JAPAN STATISTICAL SOCIETY

  JOURNAL OF THE JAPAN STATISTICAL SOCIETY 45 (1), 57-75, 2015

  THE JAPAN STATISTICAL SOCIETY

Keywords

• Contingency table
• independent model
• information geometry
• Kullback-Leibler divergence
• nested structure

Details

• CRID: 1390001205287648768
• NII Article ID: 130005152510
• NII Book ID: AA1105098X
• DOI: 10.14490/jjss.45.57
• ISSN: 13486365
• ISSN: 18822754
• NDL BIB ID: 026741577
• Web Site: http://id.ndl.go.jp/bib/026741577
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I026741577
• Web Site: https://www.jstage.jst.go.jp/article/jjss/45/1/45_57/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed