论文信息 - Using an approximate L1 Estimator

Using an approximate L1 Estimator

This note investigates the efficiency of using near-best or approximate L1 estimators as starting values in L1 linear programming procedures. In particular, it is shown that the total computer time can often be reduced if one first computes the least squares estimator, β, and then adjust y to y - Xβ in Barrodale and Roberts’ improved algorithm.

V. A. Sposito | V. Sposito | M. L. Hand | G. F. Mc Cormick | G. Cormick

[1] Gautam Appa,et al. On L1 and Chebyshev estimation , 1973, Math. Program..

[2] H. O. Hartley,et al. Two Linear Programming Algorithms for Unbiased Estimation of Linear Models , 1973 .

[3] N. Draper,et al. Applied Regression Analysis , 1966 .

[4] V. A. Sposito,et al. Using the $L_2 $-Estimator in $L_1 $-Estimation , 1976 .

[5] I. Barrodale,et al. An Improved Algorithm for Discrete $l_1 $ Linear Approximation , 1973 .

[6] O. J. Karst,et al. Linear Curve Fitting Using Least Deviations , 1958 .

[7] Ian Barrodale,et al. Algorithm 478: Solution of an Overdetermined System of Equations in the l1 Norm [F4] , 1974, Commun. ACM.

[8] H. M. Wagner. Linear Programming Techniques for Regression Analysis , 1959 .

[9] V. A. Sposito,et al. A Note on L 1 Estimation Based on the Median Positive Quotient , 1975 .

[10] Oscar Kempthorne,et al. Probability, Statistics, and data analysis , 1973 .

[11] E. Kiountouzis. Linear Programming Techniques in Regression Analysis , 1973 .