论文信息 - An Analysis of the Least Median of Squares Regression Problem

An Analysis of the Least Median of Squares Regression Problem

The optimization problem that arises out of the least median of squared residuals method in linear regression is analyzed. To simplify the analysis, it is replaced by an equivalent problem of minimizing the median of absolute residuals. A useful representation of the last problem is given to examine properties of the objective function and estimate the number of its local minima.

Nikolai Krivulin

[1] P. Rousseeuw. Least Median of Squares Regression , 1984 .

[2] H. Edelsbrunner,et al. Computing Least Median of Squares Regression Lines and Guided Topological Sweep , 1990 .

[3] J. Steele,et al. Time- and Space-Efficient Algorithms for Least Median of Squares Regression , 1987 .

[4] A. A. Zhigli︠a︡vskiĭ,et al. Theory of Global Random Search , 1991 .

[5] Alfio Marazzi,et al. Probabilistic algorithms for least median of squares regression , 1989 .

[6] Anthony C. Atkinson,et al. Simulated Annealing for the detection of Multiple Outliers using least squares and least median of squares fittin , 1991 .