Using an approximate L1Estimator
- 1 January 1977
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 6 (3) , 263-268
- https://doi.org/10.1080/03610917708812043
Abstract
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.Keywords
This publication has 9 references indexed in Scilit:
- Using the $L_2 $-Estimator in $L_1 $-EstimationSIAM Journal on Numerical Analysis, 1976
- A Note on L 1 Estimation Based on the Median Positive QuotientJournal of the Royal Statistical Society Series C: Applied Statistics, 1975
- Algorithm 478: Solution of an Overdetermined System of Equations in the l1 Norm [F4]Communications of the ACM, 1974
- On L1 and Chebyshev estimationMathematical Programming, 1973
- An Improved Algorithm for Discrete $l_1 $ Linear ApproximationSIAM Journal on Numerical Analysis, 1973
- Two Linear Programming Algorithms for Unbiased Estimation of Linear ModelsJournal of the American Statistical Association, 1973
- Linear Programming Techniques in Regression AnalysisJournal of the Royal Statistical Society Series C: Applied Statistics, 1973
- Linear Programming Techniques for Regression AnalysisJournal of the American Statistical Association, 1959
- Linear Curve Fitting Using Least DeviationsJournal of the American Statistical Association, 1958