Given any experimental data, i.e., observation times and measurements, the minimum distances of measured data from a fitting criterion are computed. Up to two independent model variables, e.g., time and concentration, and linear or nonlinear constraints can be handled. A statistical analysis provides confidence intervals for estimated parameters, correlation and covariance matrix, identification of significance levels for estimated parameters, and optimum experimental design. As a by-product, curve and surface fits are available.

The software runs under MS-Windows (64 bit).

For more complex modeling, e.g., based on ordinary differential, differential algebraic, partial differential or partial differential algebraic equations, see EASY-FIT ^ModelDesign. For minimizing any nonlinear functions subject to nonlinear constraints, see EASY-OPT ^Express.

Features

Screenshots

Download

Support

Articles and Resources

 

---

Features:
    · general
            arbitrary fitting criteria depending on parameters to be estimated
            additional nonlinear equality or inequality constraints
            second independent model variable called concentration
    · numerical routines
            Gauss-Newton-type SQP methods, various versions
            automatic differentiation
            alternative norms (sum of absolute values,  maximum of absolute values)
            confidence intervals for estimated parameters, correlation and covariance matrix
            identification of significance levels for estimated parameters
            extremely fast routines
   · user interface
            convenient and flexible modeling language
            'find' and 'filter' commands
            extensive report and graphics facilities, also for Gnuplot
            3D plots for two model or input variables, respectively
            in- and output of data from and to text or Excel files
    · limitations
            30 fitting criteria and data sets
            100 model variables
            2,000 time values
            3,000 experimental data
            200 linear or nonlinear constraints
              - limited by size of internal working arrays
     · modeling language (PCOMP)
            highly flexible statements depending on parameters to be estimated
            tabulated data, splines, linear and piecewise constant interpolation
            indexed variables and functions
            (nearly) no limitations for number of lines of code
   · implementation
            numerical routines in Fortran, executable outside of the GUI
            GUI in VBA, Microsoft Access 2007, run-time version included
            database with 240 examples
 

... for more information see the documentation (378 pages, 554 references) easy_fit.pdf

 

Download:

To download EASY-FIT ^Express, click here.

 

Support:

For more questions about features, installation, numerical routines, please contact

Prof. Klaus Schittkowski
Department of Computer Science	phone: (+49)921 553278
University of Bayreuth	fax: (+49)921 553238
D-95440 Bayreuth, Germany	klaus.schittkowski@uni-bayreuth.de

Attach your data fitting model in mathematical formulation to find out whether it can be treated by EASY-FIT ^Express or not.
 

Articles and Resources:

    · book: Numerical Data Fitting in Dynamical Systems, Kluwer Academic Publishers
    · documentation
    · many more publications