Gilliland's Correlation: A Case Study in Regression Analysis

  • Richard A Davis University of Minnesota Duluth

Abstract

A case study of regression analysis based on modeling Gilliland’s correlation was described for use in a computational methods course. The case study uses a familiar example to train students in nonlinear least squares regression and to use standardized residual plots for model assessment. Previously published equations for Gilliland’s correlation were reviewed improved by refitting Gilliland’s data using nonlinear least squares regression. A new two-parameter rational equation was found to be superior to previously reported Gilliland equations as the only model that meets all the theoretical end conditions without compromise. The new and improved equation for Gilliland’s correlation is recommended for preliminary shortcut methods of distillation column design and analysis.

Author Biography

Richard A Davis, University of Minnesota Duluth
Richard Davis is a Blehart Professor and Head of Chemical Engineering at the University of Minnesota Duluth. His teaching and research interests are in process modeling and simulation applied to metallurgy and environmental management. Professor Davis serves as Executive Secretary for the Chemical Engineering Honor Society Omega Chi Epsilon and is faculty advisor to the student chapter of the Society for Mining, Metallurgy, and Exploration. He earned his PhD from the University of California Santa Barbara. 
Published
2020-10-05
Section
Class and Home Problems