Using ridge regression to analysis the meteorological data in sulaimani.
Abstract
Linear regression is one of the frequently used statistical methods that have applications in all field of daily life. In a statistical perspective, the regression analysis is used for studying the relationship between a dependent variable and a set of independent variables. The ridge regression is the most widely model in solving the multicolinearity problem, and it''''s an alternative to OLS.Multicollinearity is the most common problem in multiple regression models in which there exists a perfect relationship between two explanatory variables or more in the model. In this study, ridge regression model was used to estimate linear regression model. This result was compared with result obtained using ordinary least squares model in order to find the best regression model. We have used meteorological data in this study. The results showed that the ridge regression method can be used to resolve the multicollinearity problem, without deleting the independent correlated variables of the model and able to estimate parameters with lower standard error values.
References
- Alibuhatto, M. C. (2016). Relationship between Ridge Regression Estimator and Sample Size When Multicollinearity Present among Regresses, world scientific news, 59, pp12-23.
- Dereny, M. E. and Rashwan, N. I. (2011). Solving Multicollinearity Problem Using Ridge Regression Models, International Journal of Contempt Mathematic Sciences, Vol.6, No.12, pp585-600.
- El- Sibakhi, R. A. (2016). A Comparative Study of Ridge Regression and Staged Logistic Regression as a Remedy of Multicollinearity Problem a Case study of Armenia Demographic and Health Survey 2010, M.Sc. Thesis, Al-Azhar University- Gaza.
- Fitrianto, A. and Yik, L. C. (2014). Performance of Ridge Regression Estimator Methods on Small Sample Size by Varying Coefficients: A Simulation Study, Journal of mathematics and Statistics, Vol.10, No.1, pp25-29, doi:10.3844/jmssp.2014.25.29.
- Gullkey, D. K. and Murrhy, J. L. (1975). Directed Ridge Regression Techniques in Casas of Multicollinearity, Journal of American Statistical Association, Vol.7, No.352, pp769-775.
- Kamel, M. M., and Aboud, S. F. (2013). Ridge Regression Estimators with the Problem of Multicollinearity, Applied Mathematical Sciences, Vol.7, No, 50, pp2469-2480.
- Montgomery, D. C. and Runger, G. C. (2002). Applied Statistics and Probability for Engineers, 3rd Edition, John Wiley and Sons, Inc, USA.
- Olandrewaju, S. O., Yahaya, H. U., and Nasirru, M. O. (2017). Effects of Multicollinearity and Autocorrelation on Some Estimators in a System of Regression Equation, European Journal of Statistics and Probability , Vol.5, No,3, pp1-15.
- Raheem, M. R., Udoh, N. S. and Gbolahan, A. T. (2019). Choosing Appropriate Regression Model in the presence of Multicolinearity, Open Journal of Statistics, 9, pp 159-168.
- Rawlings, J. O., Pantula, S. G. and Dickey, D. A. (1998). Applied Regression Analysis: A Research Tool, 2nd edition, Springer- Verlag, Inc, New York.
- Salh, S. M. (2014). Using Ridge Regression Model to Solving Multicollinearity Problem, International Journal of Scientific and Engineering Research, Vol.5, Issue 10, pp992-998.
- Tunah, D. and Siklar, E. (2015). Analysis of Inflation in Turkey via Ridge Regression, International Research Journal of Applied Finance, Vol.6, No.12, pp811-820.
- Zahari, S.M., Ramli, N. M., and Mokhtar,B. (2014). Bootstrapped Parameter Estimation in Ridge Regression with Multcollinearity and Multiple Outliers, Journal of Applied Environmental and Biological Sciences, Vol.4, No,7, pp150-156.
