An empirical approach to update multivariate regression models intended for routine industrial use

Many problems currently tackled by analysts are highly complex and, accordi ngly, multivariate regression models need to be developed. Two intertwined topics are important when such models are to be applied within the industri al routines: (i) Did the model account for the 'natural' variance of the pr oduction samples? (ii) Is the model stable on time? This paper focuses on t he second topic and it presents an empirical approach where predictive mode ls developed by using Mid-FTIR and PLS and PCR hold its utility during abou t nine months when used to predict the octane number of platforming naphtha s in a petrochemical refinery. (C) 2000 Elsevier Science Ltd. All rights re served.