models. Furthermore, using COUNTIF() function can also aid in reducing human error that may be caused by manual counting. Apart from these, model that obtained by using the modified method is free from multicollinearity and no excluded variable table will appear when it comes to running regression in the SPSS. Therefore, this modified method is recommended to be used in overcoming the weaknesses of the Z-N multicollinearity remedial method in counting frequency for identified multicollinearity source variables. ACKNOWLEDGMENTS This research was supported by the Universiti Malaysia Sabah (UMS) and the Biasiswa Kerajaan Negeri Sabah (BKNS) Scholarship. REFERENCES 1. M. H. Kutner, C. J. Nachtsheim, J. Neter and W. Li, Applied Linear Statistical Models , Boston: McGraw-Hill Irwin, 2005, pp. 278-437. 2. H. J. Zainodin, A. Noraini and S. J. Yap, Trends in Applied Sciences Research 6 : 1241-1255 (2011). 3. D. N. Gujarati and D. C. Porter, Basic Econometrics , 5 th edition, Boston: McGraw-Hill Irwin, 2009, pp. 321-346. 4. S. H. Tay, A. R. Shapiee and L. Jane, International Journal on Advanced Science Engineering Information Technology 2 : 10-15 (2011). 5. P. D. Allison, Multiple Regression: A Primer , Thousand Oaks, California: Pine Forge Press, 1999, pp. 137-139. 6. S. Q. Lafi and J. B. Kaneene, Preventive Veterinary Medicine 13 : 261-275 (1992). ICMSS 2013: International Conference on Mathematical Science & Statistics 2013.
You've reached the end of your free preview.
Want to read all 4 pages?
- Spring '18
- Dr. Moez
- Regression Analysis, multicollinearity