A New Efficient Redescending M-Estimator for Robust Fitting of Linear Regression Models in the Presence of Outliers

Table 6

Total mean square error for contaminated datasets generated from normal distribution (80% X & Y∼N(0, 1) and 20% X∼N(20, 1) and 20% Y∼N(10, 5)).

N	P	OLS	Huber	Hampel	Andrew	Tukey	Ali
N = 30	P = 2	0.545	0.537	0.324	0.317	0.325	0.312
	P = 3	0.625	0.515	0.490	0.490	0.489	0.457
	P = 6	1.036	0.695	0.656	0.771	0.766	0.623
N = 50	P = 2	0.519	0.512	0.484	0.409	0.418	0.402
	P = 3	0.526	0.450	0.433	0.408	0.416	0.403
	P = 6	0.770	0.528	0.522	0.597	0.519	0.502
N = 100	P = 2	0.514	0.505	0.499	0.413	0.417	0.401
	P = 3	0.625	0.397	0.399	0.350	0.355	0.307
	P = 6	1.035	0.385	0.390	0.360	0.363	0.349