摘要：Conceptually, a detection threshold represents the lowest concentration at which an individual or a group of individuals can reliably perceive a given stimulus, with a commonly used operational definition of 50% performance above chance. Estimated detection thresholds (DTs), however, are often reported in the literature with little attention given to the matrix in which the stimuli were evaluated. Here, we highlight the influence of matrix effects on DTs for two odor-active compounds commonly found in Vitis Labrusca wines. Differences in orthonasal DTs for methyl anthranilate (MA) and 2-aminoacetophenone (2AAP) in water, a model wine system, and wine were demonstrated using a within-subject design and forced choice (i.e., criterion free) psychophysical methods. Six sample triads, each containing two blanks and one spiked sample, were presented to participants with the instructions to choose the “different” sample, and this was repeated in different matrices (water, model wine, and wine). The estimated DTs for both compounds were significantly lower in water versus the model wine system and wine. This finding recapitulates the strong need to carefully consider the nature of the delivery matrix when determining and comparing threshold estimates across studies. Additionally, data from prior reports have suggested DTs for MA and 2AAP may differ by two orders of magnitude in spite of their structural similarity. We failed to confirm this difference here: although 2AAP thresholds were somewhat lower than MA thresholds, differences were much smaller than what had been suggested previously. This, again, emphasizes the need to make comparisons within the same individuals, using appropriate methods with sufficient numbers of participants.
