Supervised principal component regression of select paired comparisons
Supervised principal component regression (supervised PCR; SPCR) of sensory and instrumental results is conducted in new ways focusing on paired comparisons. Conventionally, SPCR is conducted on all objects. SPCR of all objects is shown to be equivalent to SPCR of all paired comparisons but different from SPCR of a subset of paired comparisons. SPCR of test-control paired comparisons is useful when the only these paired comparisons are of primary interest.
Castura, J. C., & Tomic, O. (2024). Supervised principal component regression of select paired comparisons (Preprint). Zenodo. https://doi.org/10.5281/zenodo.11663995