A new descent algorithm for the least absolute value regression problem
- 1 January 1981
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 10 (5) , 479-491
- https://doi.org/10.1080/03610918108812224
Abstract
This paper presents a new and simple algorithm for the least absolute value regression problem. It is based on the notion of “edge” descent along the surface of the objective function. It is comparable or better in computational efficiency to current linear programming approaches for roughly 4 or fewer independent variables.Keywords
This publication has 9 references indexed in Scilit:
- A revised simplex algorithm for the absolute deviation curve fitting problemCommunications in Statistics - Simulation and Computation, 1979
- Algorithm AS 132: Least Absolute Value Estimates for a Simple Linear Regression ProblemJournal of the Royal Statistical Society Series C: Applied Statistics, 1978
- Least absolute values estimation: an introductionCommunications in Statistics - Simulation and Computation, 1977
- An Iterative Technique for Absolute Deviations Curve FittingJournal of the American Statistical Association, 1973
- The Small Sample Properties of Simultaneous Equation Least Absolute Estimators vis-a-vis Least Squares EstimatorsEconometrica, 1970
- On $L_1 $ Approximation II: Computation for Discrete Functions and Discretization EffectsSIAM Journal on Numerical Analysis, 1967
- Norms for Smoothing and EstimationSIAM Review, 1964
- A Note on Curve Fitting with Minimum Deviations by Linear ProgrammingJournal of the American Statistical Association, 1961
- Linear Curve Fitting Using Least DeviationsJournal of the American Statistical Association, 1958