Developing a model for process improvement using multiple regression technique

Abstract

Purpose – Practitioners often face challenges in model development when establishing a relationship between the input and output variables and their optimization and control. The purpose of this paper is to demonstrate, with the help of a real life case example, the procedure for model development between a key process output variable, called the multi-stage flash evaporator efficiency, and the associated input process variables and their optimization using appropriate statistical and analytical techniques. Design/methodology/approach – This paper uses a case study approach showing how multiple regression methodology has been put into practice. The case study was executed in a leading Indian viscose fiber plant. Findings – The desired settings of the relevant process parameters for achieving improved efficiency have been established by appropriately using the tools and techniques from the Lean Six Sigma tool kit. The process efficiency, as measured by M3 of water evaporated per ton of steam, has improved from 3.28 to 3.48 resulting in satisfactory performance. Originality/value – This paper will be valuable to many practitioners of Six Sigma/Lean Six Sigma and researchers in terms of understanding the systematic application of quality and optimization tools in a real world situation.

Evaluating the Influence of Nutrition Determinants on Construction Workers’ Food Choices

“…The PCA also served to eliminate high correlations between the variables. Multicollinearity or high correlation between the independent variables in a regression model can make it difficult to correctly identify the most important contributors to a physical process (Sarkar, Mukhopadhyay, & Ghosh, 2014).…”