Check-all-that-apply data analysed by Partial Least Squares regression

Rinnan, Åsmund; Giacalone, Davide; Frøst, Michael

doi:10.1016/j.foodqual.2015.01.018

Cited by 11 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar explained variance results were found in sensory analysis with nontrained and trained panellists (Veramendi et al, 2013;Kostov et al, 2014). However, it is important to notice that CA explains the part of the data which holds the information of interest (Rinnan et al, 2015). Rinnan et al (2015) have indicate that, although CA is by far the most common analytical tool applied in this type of response data, the model does not contain any information regarding the uncertainty in the different attributes (which accounts for a large part of the data variation).…”

Section: Aroma Evaluationsupporting

confidence: 68%

“…This analysis showed that two factors accounted for 24% of the variability of the data. Rinnan et al (2015) have indicate that, although CA is by far the most common analytical tool applied in this type of response data, the model does not contain any information regarding the uncertainty in the different attributes (which accounts for a large part of the data variation). This low proportion is expected considering the complexity in the odour sample profile, besides when CA is used to analyse a sorting task, it could underestimate the proportion of explained variance (Veramendi et al, 2013).…”

Section: Aroma Evaluationmentioning

confidence: 99%

“…This low proportion is expected considering the complexity in the odour sample profile, besides when CA is used to analyse a sorting task, it could underestimate the proportion of explained variance (Veramendi et al, 2013). Rinnan et al (2015) have indicate that, although CA is by far the most common analytical tool applied in this type of response data, the model does not contain any information regarding the uncertainty in the different attributes (which accounts for a large part of the data variation). Therefore, the multivariate data analysis efficiently separates the information from the noise associated with the uncertainty.…”

Section: Aroma Evaluationmentioning

confidence: 99%

“…But, as the noisy part of the data is large, the explained variation could seem to be rather low. However, it is important to notice that CA explains the part of the data which holds the information of interest (Rinnan et al, 2015). Figure 2 shows the projection of the attributes and the samples in a factorial plane obtained by the CA.…”

Section: Aroma Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

Correlations of sensory parameters with physicochemical characteristics of Argentinean honeys by multivariate statistical techniques

Patrignani

Ciappini

Tananaki

et al. 2017

Int J of Food Sci Tech

View full text Add to dashboard Cite

Summary Honey acceptability is mainly determined by its colour, crystallisation degree and aroma. In the present work, the sensory characteristics and physicochemical parameters of Argentinean honeys from different ecoregions were analysed. Moisture content, Pfund colour, diastase activity, hydroxymethylfurfural content, electrical conductivity, sugar profile and volatile compounds were analytically determined in honey samples, while sensory characteristics (crystal size, fluency score, sweetness, persistence, granularity, crystallisation, colour intensity and aroma) were evaluated by a trained panel. Significant correlations were found between honey crystallisation degree and hydroxymethylfurfural content and diastase activity (P ≤ 0.05). It could be confirmed that honey crystallisation interferes with the visual perception of colour. Floral, fresh fruit, ripe fruit, balsamic and wood aromas could be successfully linked to honey volatile profile (P ≤ 0.05). These results demonstrate that the parameters that could best guarantee the consumers’ preference can be successfully associated with the chemical composition of honey by multivariate statistical analysis.

show abstract

Section: Aroma Evaluationsupporting

confidence: 68%

Section: Aroma Evaluationmentioning

confidence: 99%

Section: Aroma Evaluationmentioning

confidence: 99%

Section: Aroma Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Correlations of sensory parameters with physicochemical characteristics of Argentinean honeys by multivariate statistical techniques

Patrignani

Ciappini

Tananaki

et al. 2017

Int J of Food Sci Tech

View full text Add to dashboard Cite

show abstract

“…We considered an effect positive or negative if the associated probability of being zero was smaller than 5%. Jack-knife resampling was used to test the significance of the beta coefficient obtained from the submodels computed during the model cross-validation (Rinnan et al 2015). The cross validation was performed with 200 segments by removing seven rows (one consumer) at a time, as previously suggested for this type of data structure (Reinbach et al 2014;Rinnan et al 2015).…”

Section: Discussionmentioning

confidence: 99%

Consumer‐Led Development of Novel Sea‐Buckthorn Based Beverages

Geertsen

Allesen-Holm

Giacalone

2016

Journal of Sensory Studies

Self Cite

View full text Add to dashboard Cite

In the context of a growing interest toward foods of local origin, this research explored consumer perceptions of novel sea-buckthorn-based beverages (SBBs), developed by combining sea-buckthorn (hippophae rhamnoides L.) berries in combination with other locally sourced ingredients. Specifically, the aims of the present study were to test how newly developed SBBs were perceived compared to a selected market reference, and to determine their acceptability with a representative sample of the Danish consumer population. Using a combination of consumer-friendly product profiling methods, we investigated which product attributes were associated with different ingredient combinations. Promising prototypes were tested in a larger study where consumers (N 5 200) reported hedonic response and appropriateness of use for the SBBs. Results showed that the developed SBBs were generally well liked, but were perceived as appropriate for fewer usages than the existing ones, suggesting that consumers may find it hard to envisage how to incorporate novel SBBs in their existing dietary habits. Consumer demographics and psychographics did not significantly affect product acceptance, indicating that sensory characteristics were the most important drivers of consumer preferences within this product category. PRACTICAL APPLICATIONSThis study offers new insights into consumers' perception of novel food products of local origin. A key issue with such ingredients is that they have unique sensory properties which are unfamiliar to many consumers. We suggest evidence-based directions for product development and identify potential barriers to adoption that food producers should be aware of. Methodologically, this study shows a stepwise approach to consumer-driven product development that effectively differentiated between the products and identified most promising prototypes, and could, therefore, be beneficially applied to support product development efforts among small and medium-sized local producers.

show abstract