A New Liu-Ratio Estimator For Linear Regression Models

Abstract

In statistical modeling, regression analysis is a set of statistical processes for estimating the relationships between a dependent variable and one or more independent variables. Although there are various methods for estimating parameters, the most popular is the Ordinary Least Squares (OLS) method. However, in the presence of multicollinearity and outliers, the OLS estimator may give inaccurate values and also misleading inference results. There are many modified biased robust estimators for the simultaneous occurrence of outliers and multicollinearity in the data. In this paper, a new estimator called the Liu-Ratio Estimator (LRE), which can be used as an alternative to the Least Squares Ratio (LSR) estimator and the Ridge Ratio estimator (RRE), is proposed to mitigate the effect of 𝑦-direction outliers and multicollinearity in the data. The performance of the proposed estimator is examined in two Monte Carlo simulation studies in the presence of multicollinearity and 𝑦-direction outliers. According to the simulation results, LRE is a strong alternative to LSR and RRE in the presence of multicollinearity and 𝑦-direction outliers in the data.

Keywords

• Least Squares Ratio Estimator
• Liu Estimator
• Multicollinearity
• Ridge Estimator

References

1. Akbilgic O., Akinci E. D., 2009, A Novel Regression Approach: Least Squares Ratio, Communications in Statistics-Theory and Methods, 38, 1539-1545. google scholar
2. Arslan, O., Billor, N., 2000, Robust Liu Estimator for Regression based on an M-estimator, Journal of Applied Statistics, 27, 1, 39-47. google scholar
3. Ertaş, H., Kaçzranlar, S., Güler, H., 2017, RobustLiu-typeestimator forregressionbasedon M-estimator, Communications in Statistics-Simulation and Computation, 46, 5, 3907-3932. google scholar
4. Filzmoser, P., Kurnaz, F. S., 2018, A robust Liu regression estimator, Communications in Statistics-Simulation and Computation, 47, 2, 432-443. google scholar
5. Hoerl A.E., Kennard R.W., 1970, Ridge regression: biased estimation for nonorthogonal problems, Technometrics, 12, 1, 55-67. google scholar
6. Jadhav, N. H., Kashid, D. N., 2016, Robust Linearized Ridge M-estimator for Linear Regression Model, Communication in Statistics-Simulation and Computation, 45, 3, 1001-1024. google scholar
7. Jadhav, N. H., Kashid, D. N., 2018, Ridge Least Squares Ratio Estimator For Linear Regression Model, International Journal of Agricultural & Statistical Sciences, 14, 2, 439-447. google scholar
8. Kan, B., Alpu, O., Yazici, B., 2013, Robust Ridge and Robust Liu Estimator for Regression based on the LTS Estimator, Journal of Applied Statistics, 40, 3, 644-655. google scholar

9. Kibria, B. G., 2003, Performance of some new ridge regression estimators, Communications in Statistics: Simulation and Computation, 32, 2, 419-435. google scholar
10. Liu, K., 1993, A new class of biased estimate in linear regression, Communications in Statistics-Theory and Methods, 22, 2, 393-402. google scholar
11. Maronna, R. A., Martin, R. D., Yohai, V. J., 2006, Robust Statistics Theory and Methods, Wiley, U.K. google scholar
12. Maronna, R.A., 2011, Robust ridge regression for high-dimensional data, Technometrics, 53, 1, 44-53. google scholar
13. McDonald G.C., Galarneau D.I., 1975, A Monte Carlo evaluation of some ridge-type estimators, Journal of the American Statistical Association, 70, 350, 407-416. google scholar
14. Montgomery, D. C., Peck, E. A., Vinig, G. G., 2001, Introduction to Linear Regression Analysis, 3th. Ed. John Wiley & Sons, Inc., USA. google scholar
15. Qasim, M., Amin, M., Omer, T., 2020). Performance of some new Liu parameters for the linear regression model, Communications in Statistics-Theory and Methods, 49, 17, 4178-4196. google scholar
16. Rousseeuw P.J., Leroy, A.M., 1987, Robust Regression and Outlier Detection, Wiley, New York. google scholar
17. Silvapulle, M. J., 1991, Robust Ridge Regression based on an M-estimator, Australian Journal of Statistics, 33, 3, 319-333. google scholar