Numerical methods for the nonlinear robust regression problem
- 1 August 1981
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 13 (2) , 79-113
- https://doi.org/10.1080/00949658108810482
Abstract
Several algorithms have been proposed to solve the robust regression problem. Procedures for the incar model have well beer tested and used. In this paper two sophisticated methods are given which take in consideration the difficulties of the nonlinear case. These algorithms are programmed and tested successfully on about 100 different numerical examples.Keywords
This publication has 10 references indexed in Scilit:
- Numerical solution of robust regression problems: computational aspects, a comparisonJournal of Statistical Computation and Simulation, 1977
- On leastp-th power methods in multiple regressions and location estimationsBIT Numerical Mathematics, 1975
- A Robust Method for Multiple Linear RegressionTechnometrics, 1974
- L p -methods for robust regressionBIT Numerical Mathematics, 1974
- Ein Verfahren zur Minimierung einer Quadratsumme nichtlinearer FunktionenBiometrische Zeitschrift, 1974
- Robust Regression: Asymptotics, Conjectures and Monte CarloThe Annals of Statistics, 1973
- Spiral--A new algorithm for non-linear parameter estimation using least squaresThe Computer Journal, 1970
- Minimizing a function without calculating derivativesThe Computer Journal, 1967
- A Rapidly Convergent Descent Method for MinimizationThe Computer Journal, 1963
- An Automatic Method for Finding the Greatest or Least Value of a FunctionThe Computer Journal, 1960