Finding Optimal Value for the Shrinkage Parameter in Ridge Regression via Particle Swarm Optimization
作者： Eren Bas , Vedide Rezan Uslu , Erol Egrioglu
DOI:
关键词:
摘要: A multiple regression model has got the standard assumptions. If data can not satisfy these assumptions some problems which have serious undesired effects on parameter estimates arise. One of is called multicollinearity means that there a nearly perfect linear relationship between explanatory variables used in model. This undesirable problem generally solved by using methods such as Ridge gives biased estimates. shrinks ordinary least squares estimation vector coefficients towards origin, allowing with bias but providing smaller variance. However, choice shrinkage k ridge another issue. In this study, new algorithm based particle swarm optimization proposed to find optimal parameter.
sapub.org参考文章(23)
Gülesen Üstündagˇ Şiray, Selahattin Kaçıranlar, Sadullah Sakallıoğlu, r − k Class estimator in the linear regression model with correlated errors Statistical Papers. ,vol. 55, pp. 393- 407 ,(2014) , 10.1007/S00362-012-0484-8
Ryo Uemukai, Small sample properties of a ridge regression estimator when there exist omitted variables Statistical Papers. ,vol. 52, pp. 953- 969 ,(2011) , 10.1007/S00362-009-0303-Z
Gülin Tabakan, Fikri Akdeniz, Difference-based ridge estimator of parameters in partial linear model Statistical Papers. ,vol. 51, pp. 357- 368 ,(2010) , 10.1007/S00362-008-0192-6
Sadullah Sakallıoğlu, Selahattin Kaçıranlar, A new biased estimator based on ridge estimation Statistical Papers. ,vol. 49, pp. 669- 689 ,(2008) , 10.1007/S00362-006-0037-0
Esra Akdeniz Duran, Fikri Akdeniz, Efficiency of the modified jackknifed Liu-type estimator Statistical Papers. ,vol. 53, pp. 265- 280 ,(2012) , 10.1007/S00362-010-0334-5
Arthur E. Hoerl, Robert W. Kennard, Ridge regression iterative estimation of the biasing parameter Communications in Statistics-theory and Methods. ,vol. 5, pp. 77- 88 ,(1976) , 10.1080/03610927608827333
Dean W. Wichern, Gilbert A. Churchill, A Comparison of Ridge Estimators Technometrics. ,vol. 20, pp. 301- 311 ,(1978) , 10.1080/00401706.1978.10489675
Arthur E. Hoerl, Robert W. Kennard, Ridge Regression: Applications to Nonorthogonal Problems Technometrics. ,vol. 12, pp. 69- 82 ,(1970) , 10.1080/00401706.1970.10488635
M. A. Alkhamisi, Simulation study of new estimators combining the SUR ridge regression and the restricted least squares methodologies Statistical Papers. ,vol. 51, pp. 651- 672 ,(2010) , 10.1007/S00362-008-0151-2
Lennart Nordberg, A procedure for determination of a good ridge parameter in linear regression Communications in Statistics - Simulation and Computation. ,vol. 11, pp. 285- 309 ,(1982) , 10.1080/03610918208812264