Multiple correspondence analysis technique used in analyzing the categorical data in social sciences

AKTÜRK D., Gün S., Kumuk T.

Journal of Applied Sciences, cilt.7, sa.4, ss.585-588, 2007 (Scopus) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 7 Sayı: 4
  • Basım Tarihi: 2007
  • Doi Numarası: 10.3923/jas.2007.585.588
  • Dergi Adı: Journal of Applied Sciences
  • Derginin Tarandığı İndeksler: Scopus, Aerospace Database, Aquatic Science & Fisheries Abstracts (ASFA), Communication Abstracts, Metadex, Pollution Abstracts, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.585-588
  • Anahtar Kelimeler: Categorical data, Correspondence analysis, Social sciences, Variable
  • Ankara Üniversitesi Adresli: Evet

Özet

It is observed that Chi-square, Fisher's Exact Probability Test, G-statistics and Z-test are frequently used in social sciences to interpret the data statistically. However, exploitation of these tests depends on some conditions. Even though these conditions are met there are still problems in interpretation of the results because the obtained data are general and limited. In this study, practical limitations of the above-mentioned tests are discussed. Then, an in-depth analysis follows on advantages and exploitation of Multiple Correspondence Analysis, which is suggested as the alternative technique that resolves the limitations of other techniques mentioned above. © 2007 Asian Network for Scientific Information.