Non-Linear Least Squares Regression©
Sidney H. Young
**Sid Young died in 2004 after a long illness. He was a beloved teacher and a leader in the development and use of Mathcad as a tool to promote student learning in physical chemistry. A memorial to Dr. Young was established by the University of South Alabama ACS Student Affiliate, http://www.southalabama.edu/acs/memorial.html

Andrzej Wierzbicki
Department of Chemistry
University of South Alabama
Mobile, AL 36688
United States
mail to: wierzb@andy.chem.usouthal.edu

Nonlinear least squares regression is often required in the Physical Chemistry Laboratory. This template demonstrates various implicit and explicit methods for determination of the parameters of the regressed curve. It will produce standard deviation of fit, and standard deviations of the parameters. Residual analysis is used to demonstrate techniques of removing bad data points from the fit. Data may be read into the template by editing in a Read statement. Minor editing will then let the template be used for a variety of applications. As in the previous template, Linear Least Squares Regression, the parameters will be tested to see if their addition in the model is statistically significant. (The Mathcad 6 and Mathcad 7 versions are identical except for the subscripts in the first graph.)
Editor's Commentary
Audiences: Second-Year Undergraduate
Pedagogies: Computer-Based Learning
Domains: Analytical Chemistry, Laboratory Instruction, Physical Chemistry
Topics: Chemometrics, Mathematics / Symbolic Mathematics
File NameDescriptionSoftware TypeSoftware Version
NonLinearLeastSquares.mcd JCE Mathcad Computational Document Mathcad
nonlinear.prn JCE Data File
NonLinearLeastSquares.pdf Read-Only Document
JCE JCE Subscribers only: name and password or institutional IP number access required.
Young, S. H.; Wierzbicki, A. J. Chem. Educ. 2000, 77, 669.
Comments to: Andrzej Wierzbicki at wierzb@andy.chem.usouthal.edu
©Copyright 2004 Journal of Chemical Education