Research Article
BibTex RIS Cite

Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size

Year 2013, , 28 - 32, 01.01.2013
https://doi.org/10.5152/balkanmedj.2012.070

Abstract

Objective: The aim of study is to introduce method of Soft Independent Modeling of Class Analogy (SIMCA), and to express whether the method is affected from the number of independent variables, the relationship between variables and sample size. Study Design: Simulation study. Material and Methods: SIMCA model is performed in two stages. In order to determine whether the method is influenced by the number of independent variables, the relationship between variables and sample size, simulations were done. Conditions in which sample sizes in both groups are equal, and where there are 30, 100 and 1000 samples; where the number of variables is 2, 3, 5, 10, 50 and 100; moreover where the relationship between variables are quite high, in medium level and quite low were mentioned. Results: Average classification accuracy of simulation results which were carried out 1000 times for each possible condition of trial plan were given as tables. Conclusion: It is seen that diagnostic accuracy results increase as the number of independent variables increase. SIMCA method is a method in which the relationship between variables are quite high, the number of independent variables are many in number and where there are outlier values in the data that can be used in conditions having outlier values. Turkish Başlık: Analojik Sınıflamada Esnek Bağımsız Modelinin (ASEBAM), Bağımsız Değişkenler Arasındaki İlişki, Bağımsız Değişken Sayısı ve Örneklem Büyüklüğünden Etkilenme Durumu Anahtar Kelimeler: Sınıflama, Çoklu bağımlılık, Aşırı uç değer Amaç: Çalışmanın amacı, Analojik Sınıflamada Esnek Bağımsız Model (ASEBAM) yöntemi tanıtmak, yöntemin bağımsız değişken sayısı, değişkenler arasındaki ilişki durumu ve örneklem büyüklüğünden etkilenip etkilenmediğini ortaya koymaktır. Gereç ve Yöntemler: ASEBAM modeli iki aşamada gerçekleştirilmektedir. Yöntemin bağımsız değişken sayısı, değişkenler arasındaki ilişki ve örneklem büyüklüğünden etkilenip etkilenmediğini ortaya koymak amacı ile simülasyon denemeleri yapılmıştır. Her iki gruptaki örneklem büyüklüklerinin eşit ve 30, 100 ve 1000 olduğu, değişken sayısının 2, 3, 5, 10, 50 ve 100 olduğu durumlar, ayrıca değişkenler arasındaki ilişkilerin çok yüksek (0.95), orta düzeyde (0.50) ve çok düşük (0.05) olduğu durumlar dikkate alınmıştır. Her bir kombinasyon 1000 kez denenmiştir. Bulgular: Deneme planına ait her bir olası durum için 1000 kez gerçekleştirilen simülasyon sonuçlarının ortalama sınıflama doğrulukları tablo halinde verilmiştir. Sonuç: Bağımsız değişken sayısı artıkça diagnostik doğruluk sonuçlarının artığı görülmektedir. ASEBAM metodu değişkenler arasında ilişkilerin çok yüksek, bağımsız değişken sayısının çok fazla ve veride aşırı uç değerlerin var olduğu durumda da kullanılabilecek istatistik anlamlılık değeri var olan bir yöntemdir.

References

  • Srivastava MS. Methods of Multivariate Statistics. Eds:Balding DJ, Bloomfield P, Cressie NAC, A John Wiley&Sons Inc, Canada, 200 p.246-65. Mcclave JT, Benson GP, Sincich T. Statistics for Business and Economics. 7 th ed, Upper Saddle River N. J, Prentice Hall, 1998. p.551-552.
  • Lattin MJ, Carroll DJ, Green P. Analyzing Multivariate Data. Brooks/Cole-Thompson, Pacific Grove CA, 2003. p.426-428.
  • Wold S. Pattern Recognition by Means of Disjoint Principal Components Models. Pattern Recogn 1976;8:127-39. [CrossRef]
  • Sİrensen B, Falk ES, Wislİff-Nilsen E, Bjorvatn B, Kristiansen BE. Multivariate analysis of Neisseria DNA restriction endonuclease patterns. J Gen Microbiol 1985;131:3099-104.
  • Bylesjö M, Rantalainen M, Cloarec O, Nicholoson JK, Holmes E, Trygg J. OPLS Discriminant Analysis:Combining the Strengths of PLS-DA and SIMCA Classification. J Chemomet 2006;20:341-51. [CrossRef]
  • Lopez-de-Alba P, Lopez-Martinez L, Cerda V, Amador-Hernandez A. Simulaneous Determination and Classification of Riboflavini Thiamine, Niotinamide and Pyridoxine in Phamaceutical Formulations, by UV-Visible Spectrophotometry and Multivariate Analysis. J Braz Chem Soc 2006;17:715-22. [CrossRef]
  • Maesschalck RD, Candolfi A, Massart DL, Heuerding S. Decision criteria for soft independent modelling of class analogy applied to near infrared data. Chemometr Intell Lab 1999;47:65-77. [CrossRef]
  • Branden KV, Hubert M. Robust classification in High Dimensions based on the SIMCA Method. Chemometr Intell Lab 2005;79:10 [CrossRef]
  • Gemperline P, Webber LD. Raw materials testing using soft independent modelling of class analogy analysis of near-infrared reflectance spectra. J Am Chem Soc 1989;61:138-44.
  • Esbensen KH. SIMCA:An Introduction to Classification. Houmoller LP, eds. Multivariate data analysis in practice:An Introduction to multivariate Stata Analysis and Experimental Design. 5 th ed, Camo process AS, 2005.p:348-51.
  • Dunn WJ, Emery SL, Glen WG. Preprocessing, variable selection and classification rules in the application of simca pattern recognition to mass spectral data. Environ Sci and Technol 1989;23:1499-505. [CrossRef]
  • Zhu M, Shi Y, Li A, He J. A dinamic committee scheme on multiple-criteria linear programming classification method. Computational Science ICCS. 2007;4488:401-8.
  • Chen LF, Liao HYM, Ko MT, Lin JC, Yu GY. A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recogn 2000;33:1713-26. [CrossRef]
  • Breiman L, Friedman JH, Olshen RA, Stone CJ. Introduction to Tree Classification. Classification and Regression Trees. 1st ed, London, Chapman & Hall, 2003. p. 18-55.
  • Friedman JH. Multivariate Adaptive Regression Splines. Ann Stat 1991;19:1-141. [CrossRef]

Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size

Year 2013, , 28 - 32, 01.01.2013
https://doi.org/10.5152/balkanmedj.2012.070

Abstract

References

  • Srivastava MS. Methods of Multivariate Statistics. Eds:Balding DJ, Bloomfield P, Cressie NAC, A John Wiley&Sons Inc, Canada, 200 p.246-65. Mcclave JT, Benson GP, Sincich T. Statistics for Business and Economics. 7 th ed, Upper Saddle River N. J, Prentice Hall, 1998. p.551-552.
  • Lattin MJ, Carroll DJ, Green P. Analyzing Multivariate Data. Brooks/Cole-Thompson, Pacific Grove CA, 2003. p.426-428.
  • Wold S. Pattern Recognition by Means of Disjoint Principal Components Models. Pattern Recogn 1976;8:127-39. [CrossRef]
  • Sİrensen B, Falk ES, Wislİff-Nilsen E, Bjorvatn B, Kristiansen BE. Multivariate analysis of Neisseria DNA restriction endonuclease patterns. J Gen Microbiol 1985;131:3099-104.
  • Bylesjö M, Rantalainen M, Cloarec O, Nicholoson JK, Holmes E, Trygg J. OPLS Discriminant Analysis:Combining the Strengths of PLS-DA and SIMCA Classification. J Chemomet 2006;20:341-51. [CrossRef]
  • Lopez-de-Alba P, Lopez-Martinez L, Cerda V, Amador-Hernandez A. Simulaneous Determination and Classification of Riboflavini Thiamine, Niotinamide and Pyridoxine in Phamaceutical Formulations, by UV-Visible Spectrophotometry and Multivariate Analysis. J Braz Chem Soc 2006;17:715-22. [CrossRef]
  • Maesschalck RD, Candolfi A, Massart DL, Heuerding S. Decision criteria for soft independent modelling of class analogy applied to near infrared data. Chemometr Intell Lab 1999;47:65-77. [CrossRef]
  • Branden KV, Hubert M. Robust classification in High Dimensions based on the SIMCA Method. Chemometr Intell Lab 2005;79:10 [CrossRef]
  • Gemperline P, Webber LD. Raw materials testing using soft independent modelling of class analogy analysis of near-infrared reflectance spectra. J Am Chem Soc 1989;61:138-44.
  • Esbensen KH. SIMCA:An Introduction to Classification. Houmoller LP, eds. Multivariate data analysis in practice:An Introduction to multivariate Stata Analysis and Experimental Design. 5 th ed, Camo process AS, 2005.p:348-51.
  • Dunn WJ, Emery SL, Glen WG. Preprocessing, variable selection and classification rules in the application of simca pattern recognition to mass spectral data. Environ Sci and Technol 1989;23:1499-505. [CrossRef]
  • Zhu M, Shi Y, Li A, He J. A dinamic committee scheme on multiple-criteria linear programming classification method. Computational Science ICCS. 2007;4488:401-8.
  • Chen LF, Liao HYM, Ko MT, Lin JC, Yu GY. A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recogn 2000;33:1713-26. [CrossRef]
  • Breiman L, Friedman JH, Olshen RA, Stone CJ. Introduction to Tree Classification. Classification and Regression Trees. 1st ed, London, Chapman & Hall, 2003. p. 18-55.
  • Friedman JH. Multivariate Adaptive Regression Splines. Ann Stat 1991;19:1-141. [CrossRef]
There are 15 citations in total.

Details

Primary Language English
Subjects Health Care Administration
Journal Section Articles
Authors

Emine Arzu Kanık This is me

Gülhan Orekici Temel This is me

Semra Erdoğan This is me

İrem Ersöz Kaya This is me

Publication Date January 1, 2013
Published in Issue Year 2013

Cite

APA Kanık, E. A., Temel, G. O., Erdoğan, S., Kaya, İ. E. (2013). Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size. Balkan Medical Journal, 2013(1), 28-32. https://doi.org/10.5152/balkanmedj.2012.070
AMA Kanık EA, Temel GO, Erdoğan S, Kaya İE. Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size. Balkan Medical Journal. January 2013;2013(1):28-32. doi:10.5152/balkanmedj.2012.070
Chicago Kanık, Emine Arzu, Gülhan Orekici Temel, Semra Erdoğan, and İrem Ersöz Kaya. “Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size”. Balkan Medical Journal 2013, no. 1 (January 2013): 28-32. https://doi.org/10.5152/balkanmedj.2012.070.
EndNote Kanık EA, Temel GO, Erdoğan S, Kaya İE (January 1, 2013) Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size. Balkan Medical Journal 2013 1 28–32.
IEEE E. A. Kanık, G. O. Temel, S. Erdoğan, and İ. E. Kaya, “Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size”, Balkan Medical Journal, vol. 2013, no. 1, pp. 28–32, 2013, doi: 10.5152/balkanmedj.2012.070.
ISNAD Kanık, Emine Arzu et al. “Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size”. Balkan Medical Journal 2013/1 (January 2013), 28-32. https://doi.org/10.5152/balkanmedj.2012.070.
JAMA Kanık EA, Temel GO, Erdoğan S, Kaya İE. Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size. Balkan Medical Journal. 2013;2013:28–32.
MLA Kanık, Emine Arzu et al. “Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size”. Balkan Medical Journal, vol. 2013, no. 1, 2013, pp. 28-32, doi:10.5152/balkanmedj.2012.070.
Vancouver Kanık EA, Temel GO, Erdoğan S, Kaya İE. Affected States Soft Independent Modeling by Class Analogy from the Relation Between Independent Variables, Number of Independent Variables and Sample Size. Balkan Medical Journal. 2013;2013(1):28-32.