Comparison of Binary Logistic Regression Models Based on Bootstrap Method: An Application on Coronary Artery Disease Data

Year 2019, Volume: 32 Issue: 1, 318 - 331, 01.03.2019

Hayriye Esra Akyuz Hamza Gamgam

Abstract

This study is aimed to obtain
an appropriate logistic regression model based on the bootstrap methods. For
this purpose, two bootstrap methods called bootstrap I and bootstrap II are
given to obtain the estimations of parameters and standard errors. Traditional
logistic regression is compared with the bootstrap I and bootstrap II methods
in terms of the parameter estimations and standard errors. It has been found
that the standard errors of the parameter estimations for the bootstrap I model
are smaller than others. Also, the average widths of confidence interval based
on bootstrap I model are narrower than the logistic regression and bootstrap
II. It is seen that, the simulation study based on different sample sizes
supports these results. It can be said that the bootstrap I model based on
resampling of errors term is the best in estimating coronary artery disease.

Keywords

Bootstrap, Backward Elimination, Coronary Artery Disease, Logistic Regression, Parameter Estimation, Backward Elimination, Coronary Artery Disease, Error Term, Logistic Regression, Parameter Estimation

References

• 1. Alpar, R., Uygulamalı Çok Değişkenli İstatistiksel Yöntemler, Detay Yayıncılık, Ankara; (2011) (In Turkish).
• 2. Kleinbaum, D., Klein, M., Logistic Regression- A Self Learning Text, II ed. New York, NY: Springer; (2002).
• 3. Berkson, J., “Application of the logistic function to bio-assay”, J. Am. Stat. Assoc., 39(227): 357–365, (1944).
• 4. Lim, E., Ali, Z.A., Barlow, C.W., Jackson, C.H., Hosseinpour, A.R., Halstead, J.C., et al., “A simple model to predict coronary disease in patients undergoing operation for mitral regurgitation”, Ann. Thorac. Surg., 75(6):1820-1825, (2003).
• 5. Vupa, O., Çelikoğlu, C., “Model building in logistic regression models about lung cancer data”, Anadolu Univ. J. Sci. Tech., 7(1): 127–141, (2006).
• 6. Coşkun, S., Kartal, M., Coşkun, A., Bircan, H., “Lojistik regresyon analizinin incelenmesi ve diş hekimliğinde bir uygulaması”, Cumhuriyet Üniversitesi Diş Hekimliği Fakültesi Dergisi, 7(1): 42–50, (2004), (In Turkish).
• 7. Hirashiki, A., Yamada, Y., Murase, Y., Hirashiki, A., Yamada, Y., Murase, Y., “Association of gene polymorphisms with coronary artery disease in low- or high-risk subjects defined by conventional risk factors”, J. Am. Coll. Cardiol., 42(8): 1429–1437, (2003).
• 8. Horibe, H., Yamada, Y., Ichihara, S., Watarai, M., Yanase, M., Takemoto, K., et al., “Genetic risk for restenosis after coronary balloon angioplasty”, Atherosclerosis, 174(1): 181–187, (2004).
• 9. Çolak, C., Çolak, M.C., Orman, M.N., “The Comparison of logistic regression model selection methods for the prediction of coronary artery disease”, The Anatol. J. Cardiol., 7(1): 6–12, (2007), (In Turkish).
• 10. Atabey, Ö. “Lojistik regresyon modeli ve geriye doğru eliminasyon yöntemiyle değişken seçiminin hipertansiyon riski üzerine uygulamasında bootstrap yöntemi”, Gazi Üniversitesi, Fen Bilimleri Enstitüsü, Yüksek Lisans Tezi, Ankara, (2010), (In Turkish).
• 11. Yan, T., Zhang, G.X., Li, B.L., Han, L., Zang, J.J., Li, L., Xu, Z.Y., “Prediction of coronary artery disease in patients undergoing operations for rheumatic aortic valve disease”, Clin. Cardiol., 35(11): 707-711, (2012).
• 12. Gündoğdu, F., Özdemir, Ö., Sevimli, S., Açıkel, M., Pirim, İ., Karakelleoğlu, Ş., et al., “The relationship between interleukin-6 polymorphism and the extent of coronary artery disease in patients with acute coronary syndrome”, Arch. Turk. Soc. Cardiol., 35(5): 278–283, (2007).
• 13. Yin, Y., Li, J., Zhang, M., Wang, J., Li, B., Liu, Y., et al., “Influence of interleukin-6 gene -174g>c polymorphism on development of atherosclerosis: a meta-analysis of 50 studies involving, 33.514 subjects”, Gene, 529: 94–103, (2013).
• 14. Elsaid, A., Abdel-Aziz, A.F., Elmougy, R., Elwaseef, A.M., “Association of polymorphisms G (-174) C in IL-6 gene and G (-1082) A in IL-10 gene with traditional cardiovascular risk factors in patients with coronary artery disease”, Indian J. Biochem. Biophys., 51: 282–292, (2014).
• 15. Roger, V.L., Go, A.S., Lloyd-Jones, D.M., Benjamin, E.J., Berry, J.D., Borden, W.B., et al., “Executive summary: heart disease and stroke statistics-2012 update: a report from the american heart association”, Circ., 125(1): 188–197, (2012).
• 16. Onat, A., Yüksel, M., Köroğlu, B., Gümrükçüoğlu, H.A., Aydın, M., Çakmak, H.A., “Turkish adult risk factor study survey 2012: overall and coronary mortality and trends in the prevalence of metabolic syndrome”, Arch. Turk. Soc. Cardiol., 41: 373–378, (2013).
• 17. Anderson, D.R., Poterucha, J.T., Mikuls, T.R., Duryee, M.J., Garvin, R.P., Klassen, L.W., et al., “IL-6 and its receptors in coronary artery disease and acute myocardial infarction”, Cytokine, 62(3): 395-400, (2013).
• 18. Teixeira, B.C., Lopes, A.L., Macedo, R.C.O., Correa, C.S., Ramis, T.R., Ribeiro, J.L., et al., “Inflammatory markers, endothelial function and cardiovascular risk”, J. Vascul. Brasileiro, 13(2): 108–115, (2014).
• 19. Hosmer, D., Lemeshow, S., Sturdıvant, R., Applied Logistic Regression. Canada: Wiley&Sons Publications, (2013).
• 20. Mammen, E., When Does Bootstrap Work?. USA: Springer-Verlag New York, (1992).
• 21. Özdemir, A., “Doğrusal olmayan regresyonda asimptotik yöntemle bootstrap örneklemesi”, Yüksek Lisans Tezi, Yıldız Teknik Üniversitesi, Fen Bilimleri Enstitüsü, İstanbul, (2011), (In Turkish).
• 22. Aktükün, A. “Asal bileşenler analizinde bootstrap yaklaşımı”, İstanbul Üniversitesi İktisat Fakültesi Ekonomi ve İstatistik Dergisi, 1: 1–11, (2005), (In Turkish).
• 23. Chernick, M.R., Bootstrap Methods. (2nd edition). Canada: John Wiley and Sons, (1999).
• 24. Efron, B., Tibshirani RJ. An Introduction to the Bootstrap. Chapman & Hall, New York USA, (1993).
• 25. Bendel, R.B., Afifi, A.A., “Comparison of stopping rules in forward stepwise regression”, J. Am. Stat. Assoc., 72(357): 46-53, (1977).
• 26. Mickey, R.M., Greenland, S., “The impact of confounder selection criteria on effect estimation”, Am. J. Epidemiol., 129(1): 125-137, (1989).