Using an approximate L1Estimator
作者:
V. A. Sposito,
M. L. Hand,
G. F. Mc Cormick,
期刊:
Communications in Statistics - Simulation and Computation
(Taylor Available online 1977)
卷期:
Volume 6,
issue 3
页码: 263-268
ISSN:0361-0918
年代: 1977
DOI:10.1080/03610917708812043
出版商: Marcel Dekker, Inc.
关键词: least absolute value;efficiency of near-best estimators;linear programming;Barrodale and Roberts’ algo-rithm;modified simplex algorithm;least squares estimators
数据来源: Taylor
摘要:
This note investigates the efficiency of using near-best or approximate L1estimators as starting values in L1linear 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.
点击下载:
PDF (172KB)
返 回