Error Estimation Using the Simplex Method in Nonlinear Least Squares Data Analysis.
Abstract
The simplex method is a widely-used technique in analytical chemistry. Although primarily viewed as a technique for experimental optimization, this method is also used for mathematical modeling, such as nonlinear least squares curve fitting. Acceptable methods of chemical data analysis require estimates of both the parameter values and their errors - something which is not provided by current simplex algorithms. This paper proposes a procedure for obtaining error estimates of the fitted parameters. The proposed method can be easily implemented on a laboratory minicomputer, greatly enhancing the utility of the simplex method to analytical chemists. This procedure is first described for a general function, and then illustrated using a data set from the literature. Keywords: Ultrasonic absorption; Metal ion complexation kinetics; Computations.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 17, 1987
- Accession Number
- ADA181834
Entities
People
- Edward M. Eyring
- Gregory R. Phillips
Organizations
- University of Utah