1,721,095 research outputs found
Handling individual differences in preference mapping models
No full textIn this work we discuss an extension in preference mapping of the method proposed in Endrizzi et al. (2011) for accommodating both population averages and individual differences in the same model. The method, based on average estimates and residuals, is a combination of ANOVA, PCA and PLS-DA, which are well-known techniques that can be run in almost all statistical software packages. Main attention will be given to the relation between the double centered residual matrix which highlights differences between consumers in their relative position as compared to the average consumer values and the standard centering in preference mapping. This approach has been found particularly useful for highlighting differences in preference pattern among the consumers. Furthermore, the interpretation and the segmentation, that is here taking place based on differences in acceptance pattern, are graphically oriented. In addition, some possible alternatives to the generally used validation method in PCA are suggested. The approach is then illustrated using the data-set from a consumer study of berry fruit juices (Endrizzi et al.,2009), showing that when individual differences are analysed by the present method, interesting results regarding individual differences in response pattern were detected.
Endrizzi, I., Menichelli, E., Johansen, S. B., Olsen, N. V., & Næs, T. (2011). Handling of individual differences in rating-based conjoint analysis. Food Quality and Preference, 22, 241-254.
Endrizzi I., Pirretti G., Caló D.G., Gasperi F. (2009). A consumer study of fresh juices containing berry fruits. Journal of the Science of Food and Agriculture, 89, 1227-1235
Extension of SO-PLS to multi-way arrays: SO-N-PLS
No full textMulti-way data arrays are becoming more common in several fields of science. For instance, analytical instruments can sometimes collect signals at different modes simultaneously, as e.g. fluorescence and LC/GC-MS. Higher order data can also arise from sensory science, were product scores can be reported as function of sample, judge and attribute. Another example is process monitoring, where several process variables can be measured over time for several batches. In addition, so-called multi-block data sets where several blocks of data explain the same set of samples are becoming more common. Several methods exist for analyzing either multi-way or multi block data, but there has been little attention on methods that combine these two data properties. A common procedure is to "unfold" multi-way arrays in order to obtain two-way data tables on which classical multi-block methods can be applied. However, it is a known fact that unfolding can lead to overfitted models due to increased flexibility in parameter estimation. In this paper we present a novel multi-block regression method that can handle multi-way data blocks. This method is a combination of a multi-block method called Sequential and Orthogonalized-PLS (SO-PLS) and the multi-way version of PLS, N-PLS. The new method is therefore called SO-N-PLS. We have compared the method to Multi-block-PLS (MB-PLS) and SO-PLS on unfolded data. We investigate the hypotheses that SO-N-PLS has better performances on small data sets and noisy data, and that SO-N-PLS models are easier to interpret. The hypotheses are investigated by a simulation study and two real data examples; one dealing with regression and one with classification. The simulation study show that SO-N-PLS predicts better than the unfolded methods when the sample size is small and the data is noisy. This is due to the fact that it filters out the noise better than MB-PLS and SO-PLS. For the real data examples, the differences in prediction are small but the multi-way method allows easier interpretation
Young consumers’ preferences for water-saving wines: An experimental study
No full textFreshwater scarcity is becoming one of the most pressing issues of the global environmental sustainability, and agriculture is the main responsible of that scarcity. During the last decade, there has been an increasing consumers’ environmental concern about the impact of food production on water usage. This paper investigates young consumers’ preferences towards water saving wines and the determinants of willingness to pay (WTP) for these products. Data were collected through an experimental auction mechanism in Italy by assessing young consumers’ willingness to pay for three different wines (i.e. conventional-no water saving label, water saving front-of-pack labelled and water saving back-of-pack labelled). Young consumers’ (N = 200) characteristics related to their personal values, pro-environmental attitudes, wine habits, labeling attitudes and socio-demographics were also collected. Results reveal that on average young consumers are willing to pay higher prices for water saving labeled wines. Additionally, wine consumption frequency, label trust and use as well as consumers’ environmental-friendly attitude have a positive effect on willingness to pay for these wines. The current study offers valuable insights to policy makers and wine producers for product differentiation and for more efficiently targeting campaigns towards young consumers, in order to increase sustainability-labeled wine consumption
Permutation testing for validating PCA
Full text linkPermutation test as possible alternative to the commonly used cross-validation of samples for validating PCA results is suggested. The approach is then illustrated using two data-sets from consumer studies of apple and raspberry juice. Our findings show that internal validation provided by the permutation test is particularly advantageous when the data are complex as they are in the second case reported here
The use of analysis of variance and three-way factor analysis methods for studying the quality of a sensory panel
No full textIn sensory analysis a panel of assessors evaluate a collection of samples/products with
respect to a number of sensory characteristics. Assessments are collected in a threeway
data matrix crossing products, attributes and assessors. The main objective of the
experiment is to evaluate products. However, the performance of each assessor and of the
panel as a whole is of crucial importance for a successful analysis. At this aim univariate
analysis for each sensory attribute as well as multi-way analysis considering all directions
of information are usually performed. The present work studies the quality of a panel
using both methods. The basic idea is to compare results and investigate relations between
the two different analytical approaches
The Sequential and Orthogonalized PLS Regression for Multiblock Regression:Theory, Examples, and Extensions
No full textIn this chapter, the sequentially orthogonalized-PLS (SO-PLS) method and some of its main extensions are described and illustrated. Both theoretical aspects and applications on real data are discussed. SO-PLS is a multiblock regression method in which the information is extracted sequentially from the predictor blocks and there is no limitation in the number of predictors that can be handled. Moreover, the significance of the addition of any predictor block can be tested. An extension of the method for handling multiway arrays is also described and illustrated. SO-PLS and its extensions are versatile methods for both regression and classification; in both cases, they are particularly suitable from an interpretation point of view.</p
Classification trees in consumer studies for combining both product attributes and consumer preferences with additional consumer characteristics
No full textThe main objective of this paper is to describe and discuss the use of classification trees in consumer
studies. Focus will be given to the use of the method in relating segments of consumers, based on their
acceptance pattern, to additional consumer characteristics, including attitudes, habits and demographics
variables. Advantages of the method in handling typical issues from consumer studies will be discussed.
Primary interest will be given to the validation of the results, which will also be compared with results
from alternative methods widely used in consumer studies. The approach will then be illustrated by
using data from a conjoint study of apple juice
Combining analysis of variance and three‐way factor analysis methods for studying additive and multiplicative effects in sensory panel data
Full text linkData from descriptive sensory analysis are essentially three‐way data with assessors, samples and attributes as the three ways in the data set. Because of this, there are several ways that the data can be analysed. The paper focuses on the analysis of sensory characteristics of products while taking into account the individual differences among assessors. In particular, we will be interested in considering the multiplicative assessor model, which explicitly models the different usage of scale. A multivariate generalization of the model will be proposed, which allows to analyse the differences in the use of the scale with reference to the existing structure of relationships between sensory descriptors. The multivariate assessor model will be tested on a data set from milk. Relations between the proposed model and other multiplicative models like parallel factor analysis and analysis of variance will be clarified. Copyright © 2014 John Wiley & Sons, Ltd
Combining SO-PLS and linear discriminant analysis for multi-block classification
No full textThe aim of the present work is to extend the Sequentially Orthogonalized-Partial Least Squares (SO-PLS) regression method, usually used for continuous output, to situations where classification is the main purpose. For this reason SO-PLS discriminant analysis will be compared with other commonly used techniques such as Partial Least Squares-Discriminant Analysis (PLS-DA) and Multiblock-Partial Least Squares Discriminant Analysis (MB-PLS-DA). In particular we will focus on how multiblock strategies can give better discrimination than by analyzing the individual blocks. We will also show that SO-PLS discriminant analysis yields some valuable interpretation tools that give additional insight into the data. We will introduce some new ways to represent the information, taking into account both interpretation and predictive aspects
- …
