Speaker
Description
In many application fields, the variables used to measure a phenomenon are gathered into homogeneous blocks that measure partial aspects of the phenomenon. For example, in sensory analysis, the overall quality of products may depend on the taste and odor variables, etc. In consumer analysis, consumer preferences may depend on physical-chemical and sensory variables. In some contexts, a structure of relations between the different blocks may exist that gives rise to a chain of influences. Within each link, the blocks of predictor variables are called input blocks, while the block of dependent variables is called the output block. If the input blocks do not depend on any other block, then they are defined as exogenous blocks, while those that rely on other input blocks in the same relation are called intermediate blocks. If there is a chain of the relationship between the blocks, we are then dealing with what is often called a mediation model and must interpret both indirect and direct effects among blocks.
Within the scope of multiblock data analysis with a directional path among the blocks, we will present a new approach named SO‐PLS path modelling (SO‐PLS‐PM).
The approach splits the estimation into separate sequential orthogonalized PLS regressions (SO-PLS) for each output block. The new method is flexible and graphically oriented and allows for handling multidimensional blocks and diagnosing missing paths. New definitions of total, direct, indirect, and additional effects in terms of explained variances will be proposed, along with new methods for graphical representation.
In this research, some interesting properties of the method will be shown both on simulated and real data. The actual data concerns consumer, sensory and process modelling data. Results will also be compared to those of alternative path modelling methods.
Keywords: path analysis, graphical modelling, multiblock regression
References
R. Romano, O. Tomic, K.H. Liland, A. Smilde, T. Næs (2019). A comparison of two PLS‐based approaches to structural equation modeling. Journal of Chemometrics, 33 (3), e3105.
T. Næs, R. Romano, O. Tomic, I. Måge, A. Smilde, K.H. Liland. Sequential and orthogonalized PLS (SO‐PLS) regression for path analysis: Order of blocks and relations between effects. Journal of Chemometrics, 35 (10), e3243.
