Investigating test-control paired differences in flavour-molecular correlations
We investigate supervised principal component regression (SPCR) its sensory and instrumental results from a data set of eight pinot noir wines. Data include measured concentrations of volatile organic compounds from headspace—solid phase micro-extraction—gas chromatography—mass spectrometry (HS-SPME-GC-MS) and sensory descriptive analysis results on two selected sensory attributes evaluated orthonasally. We show the solution from SPCR as conducted conventionally is equivalent to the SPCR of all paired comparisons, but different from SPCR investigating only the subset of test-control paired comparisons. When only the test-control paired comparisons are of primary interest, the SPCR of the test-control paired comparisons performs especially well since the model focuses on only the relevant explanatory variables for the relevant subset of results. Focusing on the relevant subset of test-control paired comparisons provides a more useful solution that has good performance in terms of measures including R2, Q2, RMSEP.
Castura, J.C., & Tomic, O. (2024). Investigating test-control paired differences in flavour-molecular correlations. 17th Weurman Flavour Research Symposium. 24-27 September. Wageningen, The Netherlands. (Oral Presentation).