HIERARCHICAL MULTIBLOCK PLS AND PC MODELS FOR EASIER MODEL INTERPRETATION AND AS AN ALTERNATIVE TO VARIABLE SELECTION

In multivariate PLS (partial least squares projection to latent struct ures) and PC (principal components) models with many variables, plots and lists of b loadings, coefficients, VIPs, etc. become messy and res ults are difficult to interpret. There is then a strong temptation to reduce the variables to a smaller, more manageable number. This reduct ion of variables, however, often removes information, makes the interp retation misleading and seriously increases the risk of spurious model s. A better alternative is often to divide the variables into conceptu ally meaningful blocks and then apply hierarchical multiblock PLS (or PC) models. This blocking leads to two model levels: the upper level w here the relationships between blocks are modelled and the lower level showing the details of each block. On each level, 'standard' PLS or P C scores and loading plots are available for model interpretation. Thi s allows an interpretation focused on pertinent blocks and their domin ant variables. Such blocking is natural and straightforward in spectro scopy (multivariate calibration), quantitative molecular modelling (e. g. CoMFA) and process modelling. The principles of hierarchical multiv ariate PLS and PC modelling are reviewed, some problems with variable selection are discussed and the approach is illustrated for a data set with around 300 variables and 500 observations taken from a residue c atalytic cracker (RCCU) at the Statoil Mongstad refinery in Norway. (C ) 1996 by John Wiley & Sons, Ltd.