Multidimensional Preference Research Articles

A COMPARISON OF SEVEN PREFERENCE MAPPING TECHNIQUES USING FOUR SOFTWARE PROGRAMS

ABSTRACT Various methods are used to create a preference map based on different theories to model and analyze relationships between product descriptors and consumer preferences. Several programs offer solutions to understand influences and relationships between a descriptive sensory profile and consumer liking, but researchers need to know the (dis)advantages and (dis)similarities of these programs. This study compares the advantages and disadvantages of four statistical software programs and seven multivariate techniques for three empirical studies: milk, paint and fragrance. Internal and external preference mapping are included in this study. No multivariate method consistently generated a high percentage of consumers who mapped closest to their most-liked products. Also, neither the variance nor the complete solution was explained among descriptors and consumers. Of particular interest is that the high percent variance explained in descriptors and/or consumers did not guarantee a preference mean vector that was close to the most-liked product. For uncomplicated data, researchers can use any method/program to create a preference map when consumer data are highly homogenous in product liking patterns. XLSTAT PLS2 (Addinsoft, New York, NY) and Unscrambler PLS2 (passified; CAMO Software Inc., Woodbridge, NJ) are recommended for less homogenous consumer data. For complex heterogeneous data, multidimensional preference analysis is recommended for understanding consumer preference. PRACTICAL APPLICATIONS This research provides comparisons of various perceptual mapping techniques and statistical computer packages for creating preference maps. Results from the study show that when the interpretation of maps is implemented visually without supportive underlying findings from the original data and basic analyses, preference maps may be misleading. Such use appears common in the literature suggesting that analysis using preference mapping techniques is either overused or inappropriately used in some cases.

Using Corine Land Cover Habitat Database for the analysis of breeding bird habitat: case study of white storks (Ciconia ciconia) from northern Croatia

The purpose of this study was to find out whether a set of habitat characteristics, derived from the National Corine Land Cover (CLC) database of habitat types, could indicate the occurrence of white stork nests in a settlement. The analyses were performed for the settlements closer than 35 km from the Drava River (northern Croatia). Sixteen habitat characteristics were determined around 257 settlements occupied with white stork nests and 152 control sites without white stork nests within the same geographic region. We performed multivariate inspection of the data and a non-metric multidimensional preference analysis. The best variables for stork habitat selection were: distance to the nearest grassland habitat (P < 0.0001), distance to three nearest grassland habitats (P < 0.0001), altitude of the settlements above the sea level (P < 0.001), sum of distances to the three nearest agricultural mosaic habitats (P < 0.005) and standardized area proportion of forests (P < 0.05). The explanatory capacity of the model was 81.1%. We conclude that it is possible to define a small number of habitat characteristics derived from CLC database which can indicate the occurrence of white stork nests.

Eliciting Customer Preferences for Products From Navigation Behavior on the Web: A Multicriteria Decision Approach With Implicit Feedback

The goal of raising customer loyalty in electronic commerce requires an emphasis on one-to-one marketing and personalized services. To this end, it is essential to understand individual customer preferences for products. In this paper, we present a method for identifying customer preferences and recommending the most appropriate product. The identification and recommendation of such products are all based on the use of customer's real-time web usage behavior, including activities such as viewing, basket placement, and purchasing of products. Therefore, in this approach, we do not force a customer to explicitly express his or her preference information for particular products but rather capture his or her preferences from data that result from such activities. Information on the web usage behavior for the products determines the ordinal relationships among the products, which express that certain product is preferred to other products across the multiple aspects. The ordinal relationships among the products and the multiple aspects of products lead to the consideration of a multiple-criteria decision-making approach. Thus, the problem eventually results in the identification of weights attached to the multiple criteria in the multidimensional preference space constructed by the ordinal relationships among the products. The derived weights are then used for the prioritization of products that are not included in the navigation behavior due to factors such as time pressure, cognitive burden, and the like.

Normative Scoring of Multidimensional Pairwise Preference Personality Scales Using IRT: Empirical Comparisons With Other Formats

In this article, we offer some suggestions as to why tetrads and pentads have become the dominant formats for administering multidimensional forced choice (MFC) items but, in turn, raise questions regarding the underlying psychometric model and means of addressing item quality and scoring accuracy. We then focus our attention on multidimensional pairwise preference (MDPP) items and present an item response theory–based approach to constructing and modeling MDPP responses directly, assessing information at the item and scale levels, and a way of computing standard errors for trait scores and estimating scale reliability. To demonstrate the viability of this method for applied use, we show that the correspondence between MDPP scores derived from direct modeling with those obtained using single statement and unidimensional pairwise preference measures administered in a laboratory setting. Trait score correlations and criterion related validities are compared across testing formats and rating sources (i.e., self and other), and the usefulness of our model-based approach is further demonstrated by some illustrative results involving computerized adaptive tests (CAT).

Application of multidimensional scaling for marketing-mix modification: A case study on mobile phone category

This paper introduces an application of multidimensional scaling for marketing-mix modification of products at the maturity stage of product life cycle. The application is based upon the concept that marketers would benefit from mining the consumer behaviors to assist their marketing decisions. Using the preference map of multidimensional scaling method and influence-satisfaction matrix, the proposed methodology promotes marketers to analyze their current level of consumer satisfaction in the market and modify the marketing-mix based upon the current consumer preference and satisfaction. The proposed methodology adopts multidimensional preference (MDPREF) algorithm, which is designed to do multidimensional scaling of preference or evaluation data. While most applications with the multidimensional scaling have been to understand the position of a set of brands or products, the proposed methodology with MDPREF algorithm is to understand the similarities and dissimilarities among a set of marketing elements of a brand in consumer’s perception. A case example for the mobile phone category is provided.

Diversity and Cultural Use of Enset (&lt;i&gt;Enset ventricosum&lt;/i&gt; (Welw.) Cheesman) in Bonga in-situ Conservation Site, Ethiopia

Enset plant diversity and maintenance were investigated through interviews, quantitative and qualitative plant morphological analysis, nutritional analysis and field observations. Forty-two enset varieties were identified and grouped into 6 clusters, where the wild variety was an outlier. Principal components analysis also revealed the distinctiveness of the enset varieties. The study showed that, farmers in the Kaffa zone maintain many varieties along with associated myths, beliefs, songs/poems, and medicinal and ritual significance. A multidimensional preference analysis suggested the existence of a reasonable degree of consistency among farmers in naming the varieties and utilization aspects. Diversity within and between enset varieties was found to be high, and ‘perceptual distinctiveness’ of enset varieties of which farmers were minutely cognizant was significant in the recognition of variation and therefore plays a role in selection and maintenance of the existing diversity.

購買市場への選好比率行列のための分析モデル

Gravity model and it's extended model have been used as models for location analysis in geography. In these models, it was assumed that distance from the origin to the destination was given. However, it is difficult how to measure this distance since the inhabitant of the origin can access to the destination by the several access paths. Multidimensional scaling (MDS) or multidimensional preference model will be applicable in this case for recovering the map in hidden data. Other hand, MDS models try to decompose dissimilarity to distance between 2 points only and are lock of modeling the intensity of the destination or the market. A new model and method will be proposed in this paper, in which the intensity of the destination and distance between the origin and the destination is combined. An application to the real data set will be shown.

A Comparative Study of Chinese, American and Japanese Nurses’ Perceptions of Ethical Role Responsibilities

This article reports a survey of nurses in different cultural settings to reveal their perceptions of ethical role responsibilities relevant to nursing practice. Drawing on the Confucian theory of ethics, the first section attempts to understand nursing ethics in the context of multiple role relationships. The second section reports the administration of the Role Responsibilities Questionnaire (RRQ) to a sample of nurses in China (n = 413), the USA (n = 163), and Japan (n = 667). Multidimensional preference analysis revealed the patterns of rankings given by the nurses to the statements they considered as important ethical responsibilities. The Chinese nurses were more virtue based in their perception of ethical responsibilities, the American nurses were more principle based, and the Japanese nurses were more care based. The findings indicate that the RRQ is a sensitive instrument for outlining the embedded sociocultural factors that influence nurses' perceptions of ethical responsibilities in the realities of nursing practice. This study could be important in the fostering of partnerships in international nursing ethics.

The role of personal information sources on the decision-making process of Costa Rican dairy farmers

The attitudes of farmers in relation to the importance of different people as information and opinion sources (InfS) for different phases of the decision-making process were studied in 91 Costa Rican dairy farmers. The InfS studied were: Family members, Other farmers, Technical advisors, Farm staff and Commercial agents, while the phases were: Problem detection, Seeking for problem solutions, Seeking for new practices and Seeking for opinion. A Multidimensional Preference Analysis (MDPREF) was used to obtain a two-dimensional map of preference of the farmers. A factor analysis was used to define new variables representing the farmers' predilection towards the InfS. A canonical correlation analysis was performed to find-out simple and canonical correlation between farmers'/farms' characteristics and the InfS preferences. Informational profiles in the population were defined through a Cluster Analysis. The MDPREF suggests that Family members and Technical advisors were the most preferred InfS. However their relative importance changed throughout the phases. Farm staff were rated in third place and their role became more important in the ‘Problem detection’ phase. Other farmers and Commercial agents were, in general, the less preferred information sources. The former became slightly more important in the ‘Seeking for new practices’ phase. The canonical correlation analysis found three low-medium correlations between the farmers'/farms' characteristics and the InfS factors. These correlations showed that the farmers' age, educational level and dedication and the farms' characteristics of area, herd size and distance to population centres had significant influence on the preference of the farmers towards different information sources. The cluster analysis found nine groups of similar farmers according to their preferences towards informational sources. Some implications mainly for extension activities are also stated and discussed. The importance of different informational sources slightly change throughout the decision-making steps, the family and farm staff being the most preferred information sources.

Incentives and Barriers That Influence Clinical Computerization in Hong Kong: A Population-based Physician Survey

Given the slow adoption of medical informatics in Hong Kong and Asia, we sought to understand the contributory barriers and potential incentives associated with information technology implementation. A representative sample of 949 doctors (response rate = 77.0%) was asked through a postal survey to rank a list of nine barriers associated with clinical computerization according to self-perceived importance. They ranked seven incentives or catalysts that may influence computerization. We generated mean rank scores and used multidimensional preference analysis to explore key explanatory dimensions of these variables. A hierarchical cluster analysis was performed to identify homogenous subgroups of respondents. We further determined the relationships between the sets of barriers and incentives/catalysts collectively using canonical correlation. Time costs, lack of technical support and large capital investments were the biggest barriers to computerization, whereas improved office efficiency and better-quality care were ranked highest as potential incentives to computerize. Cost vs. noncost, physician-related vs. patient-related, and monetary vs. nonmonetary factors were the key dimensions explaining the barrier variables. Similarly, within-practice vs external and "push" vs "pull" factors accounted for the incentive variables. Four clusters were identified for barriers and three for incentives/catalysts. Canonical correlation revealed that respondents who were concerned with the costs of computerization also perceived financial incentives and government regulation to be important incentives/catalysts toward computerization. Those who found the potential interference with communication important also believed that the promise of improved care from computerization to be a significant incentive. This study provided evidence regarding common barriers associated with clinical computerization. Our findings also identified possible incentive strategies that may be employed to accelerate uptake of computer systems.

Commensurate ideal points

The authors remedy the shortcomings of multi-dimensional preference scaling by substituting a brief survey of directly rated preferences. Using a methodology given by Bechtel [Journal of Outcome Measurement 4 (2000) 635], this approach estimates “population-averaged” ideal points as negated mean cumulative logits (MCLs). These negated MCLs are commensurate over correlated survey items with varying numbers of response categories. Their usefulness in assessing consumer preferences is illustrated in a national product survey. This applicability extends to any rating scale used to measure a subjective variable in market and opinion research.

Client Perceptions of and Preferences for University-Based Career Services

One hundred thirty-three students who were actively seeking career services reported on their perceptions of the similarity among, and their preferences for, 17 different types of career assistance by way of a paired comparison task. Multidimensional scaling (MDS) and multidimensional preference modeling procedures were used to map these data into spatial representations. Ethnicity, international/domestic student status, tendency to foreclose (TTFS; Blustein, Ellis, & Devenis, 1989), and previous experience with an interest inventory each accounted for differences in perceptions. All participants preferred career assistance involving direct interaction with employed individuals, but class level, occupational status, previous participation in a career development class, and previous experience with career counseling accounted for differences in preferences.

Gustatory Evaluation of Still and Carbonated Waters: A Preference Rating Study.

We studied the sensory preference for six still waters and four carbonated waters, nonflavored, by 11 tasting experts (4 women and 7 men). Five tasters rated the still waters, four tasters rated the carbonated water, and seven tasters rated twice on each of the still waters when evaluated with a dry red wine. All ratings were performed through answering a set of questions regarding the specific taste and/or smell of the waters. All tasters and the statistician were blinded to the water brands during rating and analysis. Multidimensional preference analysis and correspondence analysis were used to portray the underlying sensory preference. Still waters with higher mineral content tended to be less favorable for drinking purposes. On the other hand, carbonated waters with more minerals (but not over a certain limit) were favorable, and still waters with higher mineral content were preferable as mouth cleaners for red wine. The methodology can be carried to the food and beverage industries, to the functional foods industry, and to medical research where the preference of patients toward certain medications is of interest.

Multidimensional Scaling and Preference Mapping: Promising Methods for Investigating Older Adults’ Physical Activity Perceptions and Preferences

Research on older adult physical activity promotion has lacked methods to measure older adults’ physical activity perceptions and preferences. This article describes perceptual and preference-mapping marketing techniques for investigating perceived features in physical activities. Using these techniques, investigators can represent the dimensions in which older adults perceive physical activity modes, label them, and consider individual differences. In this study, older adults compared 13 physical activities and ranked them by preference. A 4-dimensional space satisfactorily represented perceptions, and a 3-dimensional space, preferences. Physical activity perceptions varied along orthogonal dimensions of health affordance. intensity, social nature, and competitive nature. Categories of preference were revealed as dimensions relating to noncompetitive/self-efficacy attributes, intensity, and gender practices. The authors conclude that older adults’ physical activity preferences and perceptions can be represented by multiattribute dimensional spaces. Future research should employ these scaling techniques to describe relationships between older adults and multiattribute physical activities and determine how they influence perceptions, preferences, and physical activity patterns.

Perceived importance of the Internet as an information channel for OM professionals

Previous research, conducted before the Internet was widely accessible, has shown that information sources and channels can influence the initiation, adoption, and implementation of innovations. The field of operations management faces a wide variety of innovations, the eventual diffusion of which may depend on changes that are now occurring in information technology. This study uses data collected from two surveys, one conducted postally and one conducted over the Internet, to identify how operations management practitioners, consultants, academics, and students perceive and use information from various sources (books, journals, etc.) and channels (conferences, the Internet, etc.). The results indicate that the Internet is growing in importance as an information channel, with more than 40 percent of all respondents having used information obtained from the Internet during the year preceding our study. Although most respondents view that information as being less important to them professionally than information from other sources and channels, those who use the Internet most frequently have a much higher opinion of the information it provides. Multidimensional preference analysis indicates that the Internet is perceived as being quite different from traditional sources and channels, but because of that difference it currently meets the preferences of only a small subset of individuals.

Instrumental or emotional evaluations: What determines preferences?

The present study investigated the separability of two evaluative aspects, instrumental and emotional utilities, and tested the hypothesis that situational context influences the relative impact of these evaluations in decision making. Twenty-nine subjects rank ordered eight options according to their preferences. The options were hypothetical prizes the subjects could win, either in a mail lottery (private context) or in a TV show (public context). Subjects rated all options on utility scales and indicated their emotional associations. It was hypothesized that in the private context condition subjects' preferences were more influenced by emotions, whereas due to justification demands, preferences were more influenced by instrumental considerations in the public context condition. A multidimensional preference analysis yielded two dimensions. The second of these dimensions distinguished between experimental conditions. An individual differences scaling analysis yielded significantly higher subject weights for the second dimension in the public context group. The first dimension could be interpreted as mapping positive versus negative emotions, whereas the second dimension reflected instrumental evaluations. Regression analyses indicate that both instrumental and emotional evaluations significantly contribute in predicting preferences, but that the relation between preferences and evaluative dimensions is only indirect.

INDEPENDENCE OF REINFORCEMENT DELAY AND MAGNITUDE IN CONCURRENT CHAINS

A three-component concurrent-chains procedure was used to investigate preference between terminal-link schedules that differed in delay and magnitude of reinforcement. Response and time allocation data were well described by a generalized matching model. Sensitivity to delay appeared to be lower when reinforcement magnitudes were unequal than when they were equal, but when obtained rather than programmed time spent responding in the initial links was used in the model, the difference vanished. The results support independence of delay and magnitude as separate dimensions of reinforcement value, as required by the matching law, and the assumption of the contextual choice model (Grace, 1994) that sensitivities to delay and magnitude are affected similarly by temporal context. Although there was statistical evidence for interaction between successive components, the effects were small and transient. The multiple-component concurrent-chains procedure should prove useful in future research on multidimensional preference, although it may be necessary to control obtained initial-link time more precisely.

Differences in Person-Environment Congruence between Microenvironments

ABSTRACTIn the Person-Environment (P-E) Congruence model, psychological well-being is proposed to be a function of the degree of fit between the perceived environment and the important needs of the individual; and, that in more restricted environments, the relationship is stronger. The present study examined, cross-sectionally and longitudinally, the Congruence levels and well-being of elderly veterans (N = 165) in four microenvironments within a single instutition. Congruence was assessed using the multidimensional Environmental Perception, Preference and Importance Scale (EPPIS). Well-being was measured using the PGC Moral Scale, the Life Satisfaction Index A and a semantic differential self-concept scale. There were significant microenvironment differences on three of the 15 EPPIS dimensions; the P-E Congruence scores were predictive of well-being; and, the specific dimensions predictive of well-being varied across microenvironments, criterion of well-being and time. The data reinforces the notion that treatment programs must be individualized and that the P-E model, operationalized in the EPPIS, may serve as a viable clinical tool.

Multidimensional Unfolding of Children's Causal Beliefs: One Aspect of Construct Validation

A two-dimensional assessment device of children's causal beliefs was constructed on the basis of four perceived causes of success and failure consequences, given 12 situations, each describing circumstances for a consequence. The four perceived causes, ability (A), effort (E), task difficulty (T), and luck (L), were de fined in terms of two a priori dimensions (i.e., inter nality and stability) according to Weiner's (1974) the ory of causal attribution. Four hundred and fifty-nine Grade 3, 4, 5, and 6 children were asked to make preference judgments over 72 paired comparisons. The data matrices thus obtained were subjected to a multi dimensional preference scaling method based on a vector model (Carroll, 1972). The internal analysis re covered the two causal dimensions perceived by chil dren as hypothesized by the model. This internal structural aspect of the construct validity was found to be accompanied by a moderately high test-retest relia bility.

City Council Policy Orientations and Policy Development

This study examines how five city councils conceptually structure the issues that come before them. These structures are uncovered by using open-ended data gathering instruments in conjunction with nonmetric multidimensional scaling and preference mapping techniques. The results suggest that all five councils essentially share a common conceptual framework in evaluating issues. What gives each council a unique orientation within this shared framework are the subtle differences in meaning and importance that are given to their policy dimensions. The results further suggest that city councils may be conceptually limited in the number of dimensions that can be used in decision making at any given time. This limitation necessitates that city councils restructure their policy frameworks if they are to cope effectively with new community challenges.