Optimal determination of the parameters of some biased estimators using genetic algorithm

Abstract

In this paper, some new algorithms for estimating the biasing parameters of the ridge, Liu and two-parameter estimators are introduced with the help of genetic algorithm (GA). The proposed algorithms are based on minimizing some statistical measures such as mean square error (MSE), mean absolute error (MAE) and mean absolute prediction error (MAPE). At the same time, the new algorithms allow one to keep the condition number and variance inflation factors to be less than or equal to ten by means of the GA. A numerical example is presented to show the utility of the new algorithms. In addition, an extensive Monte Carlo experiment is conducted. The numerical findings prove that the proposed algorithms enable to eliminate the problem of multicollinearity and minimize the MSE, MAE and MAPE.

KEYWORDS:

• Genetic algorithm
• Liu estimator
• parameter optimization
• ridge estimator
• two-parameter estimator

Mathematics Subject Classifications:

• 62J07
• 6207
• 65K05
• 9008
• 90C90

Acknowledgments

The authors are grateful to the reviewers for their valuable comments and contributions.

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

Erkut Tekeli http://orcid.org/0000-0001-9468-5378

Selahattin Kaçıranlar http://orcid.org/0000-0003-0678-7935

Nimet Özbay http://orcid.org/0000-0003-3840-3107

Additional information

Funding

This work is supported by Çukurova University Scientific Research Projects Unit [grant number: FBA-2018-10303].