GaussFit is a new computer program for solving least squares and robust estimation problems. GaussFit is written in C computer language and especially designed to make it easy to specify complex reduction models. GaussFit uses orthogonal transformations (Householder transformations) instead of normal equations to solve the mean squares problems. A special feature of GaussFit is that it manipulates actually complex structures containing the value of an expression plus all of the relevant partial derivatives which are calculated by means of analytic formulas and not by numerical differentiation. GaussFit provides robust estimation.
Keywords for this software
References in zbMATH (referenced in 6 articles , 1 standard article )
Showing results 1 to 6 of 6.
- Aster, Richard C.; Borchers, Brian; Thurber, Clifford H.: Parameter estimation and inverse problems (2013)
- Branham, Richard L. jun.: Total least squares: An ideal mathematical tool for galactic kinematics (1998)
- Babu, G. Jogesh; Feigelson, Eric D.: Astrostatistics (1996)
- Jukić, Dragan: The problem of the initial approximation for a special nonlinear least squares problem (1996)
- Stahel, Werner A.: Research directions in robust statistics (1991)
- Jefferys, W. H.; Fitzpatrick, M. J.: GaussFit - a system for least squares and robust estimation (1987)