Selection of variables in Discrete Discriminant Analysis

Anabela Marques; Ana Sousa Ferreira; Margarida G.M.S. Cardoso

Biometrical Letters (2013)

  • Volume: 50, Issue: 1, page 1-14
  • ISSN: 1896-3811

Abstract

top
In Discrete Discriminant Analysis one often has to deal with dimensionality problems. In fact, even a moderate number of explanatory variables leads to an enormous number of possible states (outcomes) when compared to the number of objects under study, as occurs particularly in the social sciences, humanities and health-related elds. As a consequence, classi cation or discriminant models may exhibit poor performance due to the large number of parameters to be estimated. In the present paper, we discuss variable selection techniques which aim to address the issue of dimensionality. We speci cally perform classi cation using a combined model approach. In this setting, variable selection is particularly pertinent, enabling the handling of degrees of freedom and reducing computational cost.

How to cite

top

Anabela Marques, Ana Sousa Ferreira, and Margarida G.M.S. Cardoso. "Selection of variables in Discrete Discriminant Analysis." Biometrical Letters 50.1 (2013): 1-14. <http://eudml.org/doc/268691>.

@article{AnabelaMarques2013,
abstract = {In Discrete Discriminant Analysis one often has to deal with dimensionality problems. In fact, even a moderate number of explanatory variables leads to an enormous number of possible states (outcomes) when compared to the number of objects under study, as occurs particularly in the social sciences, humanities and health-related elds. As a consequence, classi cation or discriminant models may exhibit poor performance due to the large number of parameters to be estimated. In the present paper, we discuss variable selection techniques which aim to address the issue of dimensionality. We speci cally perform classi cation using a combined model approach. In this setting, variable selection is particularly pertinent, enabling the handling of degrees of freedom and reducing computational cost.},
author = {Anabela Marques, Ana Sousa Ferreira, Margarida G.M.S. Cardoso},
journal = {Biometrical Letters},
keywords = {combining models; Discrete Discriminant Analysis; variable selection},
language = {eng},
number = {1},
pages = {1-14},
title = {Selection of variables in Discrete Discriminant Analysis},
url = {http://eudml.org/doc/268691},
volume = {50},
year = {2013},
}

TY - JOUR
AU - Anabela Marques
AU - Ana Sousa Ferreira
AU - Margarida G.M.S. Cardoso
TI - Selection of variables in Discrete Discriminant Analysis
JO - Biometrical Letters
PY - 2013
VL - 50
IS - 1
SP - 1
EP - 14
AB - In Discrete Discriminant Analysis one often has to deal with dimensionality problems. In fact, even a moderate number of explanatory variables leads to an enormous number of possible states (outcomes) when compared to the number of objects under study, as occurs particularly in the social sciences, humanities and health-related elds. As a consequence, classi cation or discriminant models may exhibit poor performance due to the large number of parameters to be estimated. In the present paper, we discuss variable selection techniques which aim to address the issue of dimensionality. We speci cally perform classi cation using a combined model approach. In this setting, variable selection is particularly pertinent, enabling the handling of degrees of freedom and reducing computational cost.
LA - eng
KW - combining models; Discrete Discriminant Analysis; variable selection
UR - http://eudml.org/doc/268691
ER -

References

top
  1. Benjamini Y., Hochberg Y.(1995): Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing. Journal of the Royal Statistical Society. Series B (Methodological) 57 289-300. Zbl0809.62014
  2. Bishop C.M.(1995): Neural Networks for Pattern Recognition. Oxford University Press. Zbl0868.68096
  3. Brito I., Celeux C., Ferreira A.S.(2006): Combining Methods in Supervised Classication: a Comparative Study on Discrete and Continuous Problems. Revstat-Statistical Journal: 4(3): 201-225. Zbl1125.62059
  4. Celeux G., Mkhadri A.(1992): Discrete regularized discriminant analysis. Statistics and Computing 2(3): 143-151.[Crossref] 
  5. Celeux G., Nakache J.P.(1994): Analyse Discriminante sur Variables Qualitatives. G. Celeux et J. P. Nakache diteurs, Polytechnica. 
  6. Ferreira A.S.(2000): Combinação de Modelos em Análise Discriminante sobre Variáveis Qualitativas. PhD thesis (in portuguese), Universidade Nova de Lisboa. 
  7. Ferreira A.S.(2010): A Comparative Study on Discrete Discriminant Analysis through a Hierarchical Coupling Approach. In Classication as a Tool for Research, Studies in Classication, Data Analysis, and Knowledge Organization; Hermann Locarek-Junge, Claus Weihs (Eds.), Springer-Verlag, Heidelberg- Berlin: 137-145. 
  8. Ferreira A.S.(2004): Combining models approach in Discrete Discriminant Analysis through a committee of methods. In Classication, Clustering, and Data Mining Applications; D. Banks, L. House, F. R. McMorris, P. Arabie, W. Gaul (Eds.), Springer: 151-156. 
  9. Ferreira A.S., Cardoso M.(2010): Evaluation of Results in Discrete Discriminant Analysis. Book of Abstracts of Stochastic Modeling Techniques and Data Analysis International Conference, Skiadas, C. H. (Eds.), Chania, Creta, Grécia, Junho: 94-95. 
  10. Ferreira A.S., Celeux G., Bacelar-Nicolau H.(1999): Combining models in discrete discriminant analysis by an hierarchical coupling approach. Proceedings of the IX International Symposium of ASMDA: 159-164. 
  11. Ferreira A.S., Celeux G., Bacelar-Nicolau H.(2000): Discrete Discriminant Analysis: The performance of Combining Models by an Hierarchical Coupling Approach. In Kiers, Rasson, Groenen and Shader, editors, Data Analysis, Classication and Related Methods, Springer: 181{186. Zbl1028.62050
  12. Ferreira A.S., Celeux G., Bacelar-Nicolau H.(2001): New developments on combining models in Discrete Discriminant Analysis by a Hierarchical Coupling approach. Applied Stochastic Models and Data Analysis- ASMDA; G. Govaert, J. Janssen, N. Limnios (Eds.), UTC: 430-435. 
  13. Goldstein M., Dillon W.R.(1978): Discrete Discriminant Analysis. New York: Wiley. Zbl0396.62042
  14. Holm S.(1979): A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics 6(2): 65-70. Zbl0402.62058
  15. Marques A., Ferreira A.S., Cardoso M. (2008): Uma proposta de combinação de modelos em Análise Discriminante. Estatística - Arte de Explicar o Acaso, in Oliveira I. et al. Editores, Ci^encia Estatística, Edições S.P.E.: 393{403. 
  16. Matusita K. (1955): Decision rules based on distance for problems of fit, two samples and estimation. In Ann. Inst. Stat. Math. 26(4): 631-640.[Crossref] Zbl0065.12101
  17. Pawlak Z.(1982): Rough sets. International Journal of Computer and Information Sci. 11: 341{356. Zbl0501.68053
  18. Pearl J.(1988): Probabilistic reasoning in intelligent systems: Networks of plausible inference. Los Altos: Morgan Kaufmann. Zbl0746.68089
  19. Prazeres N.L.(1996): Ensaio de um Estudo sobre Alexitimia com o Rorschach e a Escala de Alexitimia de Toronto (TAS-20). Master Thesis, Univ. Lisbon. 
  20. Saraiva F.(2010): Satisfaçao Conjugal e relaçao coparental ao longo do ciclo vital da familia. Master Thesis, Univ. Lisbon. 
  21. Silva A.P.D.(2010): Classicaçao supervisionada para dados de elevada dimensăo. Livro de resumos das XVII Jornadas de Classicaçao e Anlise de Dados (JOCLAD 2010), ISCTE Eds. pp. 17. 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.