Handling Missing Values in Marketing Research Using SOM

  • Mariusz Grabowski
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)


Many fields of research suffer from incomplete data. In marketing the problem of incomplete information is particularly important as data losses occur quite frequently. In practice, researchers using various methods deal with this problem in many less or more satisfactory ways. This paper validates the use of SOM (Self-Organizing Map) in estimating missing data in a marketing field and refers to another non-trivial method of handling missing values called expectation maxi-mization (EM).


Garbage Disposal Miss Data Estimation Expectation Maximiza Astronomical Data Analysis Software Data Estimation Method 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. CHERKASSKY, V. and LARI-NAJAFI, H. (1991): Constrained Topological Mapping for Nonparametric Regression Analysis. Neural Networks, 4, 27–40.CrossRefGoogle Scholar
  2. GRABOWSKI, M. (1998): Application of Self-Organizing Maps to Outlier Identification and Estimation of Missing Data. In: A. Rizzi, M. Vichi, and H.H. Bock (Eds.): Advances in Data Science and Classification. Springer, Berlin, 279–286.Google Scholar
  3. JAJUGA, K. (1990): Statystyczna teoria rozpoznawania obrazw. PWN, Warszawa.Google Scholar
  4. JAJUGA, K. (1993): Statystyczna analiza wielowymiarowa. PWN, Warszawa.Google Scholar
  5. KOHONEN, T., HYNNINEN, J., KANGAS, J., and LAAKSONEN, J. (1995): SOM_PAK The Self-Organizing Map Program Package Version 3.1. Helsinki University of Technology, http://www.cis.hut.fi/research/som_pak/Google Scholar
  6. KOHONEN, T. (2001): Self-Organizing Maps. Springer, Berlin.Google Scholar
  7. KORDOS, J. (1988): Jakość danych statystycznych. PWE, Warszawa.Google Scholar
  8. LITTLE, R.J.A. and RUBIN, D.A. (1987): Statistical analysis with missing data. John Wiley and Sons, New York.Google Scholar
  9. MURTAGH, F. (1995): Unsupervised catalog classification. In: D. Shaw, J. Payne, and J. Hayes (Eds.): Astronomical Data Analysis Software and Systems IV, ASP, 264–267.Google Scholar
  10. PAWEŁEK, B. (1996): Metody szacowania brakujacych informacji w szeregach przekrojowo-czasowych. Niepublikowana praca doktorska. Akademia Ekonomiczna w Krakowie.Google Scholar
  11. POCIECHA, J. (1996): Metody statystyczne w badaniach marketingowych. PWN, Warszawa.Google Scholar
  12. SARLE, W.S. (1994): Neural Networks and Statistical Models. In: SAS Institute Inc.: Proceedings of the Nineteenth Annual SAS Users Group International Conference, Cary, NC, 1538–1550.Google Scholar
  13. ULTSCH, A. (1993): Self organized feature maps monitoring and knowledge acquisition of a chemical process. In: S. Gielen and B. Kappen (Eds.): Proceedings of the International Conference on Artificial Neural Networks (ICANN93). Springer-Verlag, London 864–867.Google Scholar
  14. WOTHKE, W. (2000): Longitudinal and multi-group modeling with missing data. (Adobe pdf format) In T.D. Little, K.U. Schnabel, and J. Baumert (Eds.): Modeling longitudinal and multiple group data: Practical issues, applied approaches and specific examples. Mahwah, NJ: Lawrence Erlbaum Associates.Google Scholar

Copyright information

© Springer-Verlag Berlin · Heidelberg 2005

Authors and Affiliations

  • Mariusz Grabowski
    • 1
  1. 1.Department of Computer ScienceCracow University of EconomicsKrakówPoland

Personalised recommendations