[AIT logo]

Institut für Astronomie und Astrophysik

Abteilung Astronomie

Sand 1, D-72076 Tübingen, Germany 		[Uni logo]


Table of Contents



Introduction

The subroutines in this subdirectory are intended to replace the IDL-delivered chi^2-minimizing subroutine curvefit with a more meaningful subroutine, jwcurvefit which knows how to keep parameters fixed ("freezing"), and how to keep certain fit-parameters within given bounds. jwcurvefit is used by fiterror to compute error bars correctly (i.e., without using the diagonal elements of the Hessian matrix at the best fit value). Finally, the subroutine steppar can be used to plot one- and two-dimensional Chi^2 contours to determine uncertainty ranges for two interesting parameters.

Index of Subroutines

fiterror compute two-sided, asymmetric error bars for a chi^2 fit
JWCURVEFIT Non-linear least squares fit to a function of an arbitrary number of parameters. The function may be any non-linear function. If available, partial derivatives can be calculated by the user function, else this routine will estimate partial derivatives with a forward difference approximation.
mpfiterror compute two-sided, asymmetric error bars for a chi^2 fit
mpsteppar plot 1D or 2D chi^2 contours for chi^2 fitting error determination
steppar plot 1D or 2D chi^2 contours for chi^2 fitting error determination
Last modified by pro2html on 2008 November 09 at 04:10 UTC

[Home Page] [Software, Documentation] [IDL Documentation] [Quick Reference] [Feedback]

Jörn Wilms ([email protected])
Updated automatically