Search

La utilización del análisis conjunto para estudiar procesos de decisión estratégica se considera un avance respecto a los métodos habituales post-hoc. Pero, dado que los experimentos conjuntos evalúan percepciones sobre perfiles del entorno descritos por frases, en lugar de preferencias, surge el problema de que la carga informativa que generan estos escenarios puede superar la capacidad del entrevistado, dificultando su evaluación y delimitando su uso a pocos factores. Este trabajo investiga cómo el diseño (el número de atributos) afecta a la complejidad de la evaluación y el rendimiento del experimento. Además, se propone un diseño mixto basado en bloques incompletos balanceados y, mediante un experimento, se compara su rendimiento frente a un diseño de bloques estándar. Los resultados muestran que la complejidad derivada del número de atributos tiene un efecto moderado en la variación explicada pero mayor en el peso de los factores, vislumbrando el uso de heurísticas distintas de los encuestados en el proceso de evaluación. The use of conjoint analysis for studying strategic decision processes is considered an improvement on the usual post-hoc methods. However, since joint experiments evaluate the perceptions of profiles of the environment, described by sentences, instead of evaluating preferences, arises the problem that the reporting burden generated by these scenarios can exceed the capacity of the respondent, hampering its assessment and limiting its use to a few factors. This paper analyzes how the design (number of attributes) affects the complexity of the evaluation and the performance of the experiment. Besides, it also proposes a mixed design based on balanced incomplete blocks, comparing by experimentation its performance against a standard blocks design. Results show that complexity derived from the number of attributes has a moderate effect on the explained variation, but a greater effect in the weight of the factors, envisioning the use of different heuristics from respondents in the assessment process. info:eu-repo/semantics/acceptedVersion

Purpose Adaptive conjoint analysis (ACA) is a market research methodology for measuring utility in business-to-business and customer studies. Based on partial profiles, ACA tailors an experiment’s design to each respondent depending on their previously stated preferences, ordered in a self-assessment questionnaire. The purpose of this paper is to describe advantages and disadvantages of using a partial-profile randomised experiment, the usual system, and to propose a new design strategy for arranging profiles in blocks that improve its performance. Design/methodology/approach The authors propose a comparison between their design with the commonly used designs, as random designs and the so-called “mirror image”, in their resolution capacity for the estimations of main factors and two-factor interactions with the lowest number of profiles. Findings Comparing the proposed design over the other two designs highlights certain aspects. The proposed design guarantees more estimation for each experiment than the others and allows the researcher to tailor the design to his or her goals. The authors’ procedure will help researchers to determine an experiment’s resolution capacity before carrying it out, as well as to estimate main factors and two-factor interactions alike. Originality/value The authors propose a new design strategy for arranging the profiles in blocks for improving the performance of ACA. This proposal is based on the use of a full-profile approach in which profiles are arranged in two-level factorial designs in blocks of two, and the levels of each factor are codified vectorially.

Identifying relevant attributes or variables is the first objective of conjoint analysis in market research. As a result of technological development, today it is common for researchers to use sequential experimental methods for adjusting design factors in successive phases. In particular, in the field of consumer behaviour these models are used predominantly for assessing subjective perceptions relating to the attributes of different products with high sensorial components (e.g. food, drinks and personal care products). This paper illustrates the use of response surface methodology in conjoint experiments, allowing sequential research in which the evaluation of a choice set determines the weight of factors in the next choice set and continues until the optimum combination is achieved. To this end we have carried out a computer simulation to determine the optimal combination of ingredients for a sauce. The simulation shows that the model needs only a few steps to reach the optimal combination of ingredients. This result indicates that response surface methodology can be considered a useful tool in the field of market research and, in particular, in studies on consumer behaviour.

The purposes of this study are to demonstrate how it is possible to determine which attributes are the most important in the final choices of tourists who use a travel agent brochure as a source of information and how these attributes influence perceived value in a pre-purchase stage.We conduct the study in three phases: (i) a qualitative study, (ii) an experiment using choice-based conjoint analysis by means of a fractional factorial experimental design and (iii) another experiment using a full factorial derived from the same design. Results suggest advertisement size, a hotel’s starred rating and price influence perceived value at this stage. The presence of a positive combined effect of price and advertising was found. Implications and directions for future applications are offered, focusing particularly on marketing services.

ResumenEl análisis conjunto es una técnica utilizada para estudiar las preferencias de los consumidores en estudios de mercado. Uno de los aspectos más importantes relacionados con el desarrollo de dicha técnica, se centra en fijar el conjunto de elección que deben evaluar los entrevistados. De forma tradicional, se utilizan diseños factoriales para estimar los valores parciales de los factores. Sin embargo, si el investigador, además, está interesado en estimar las interacciones entre dos o más factores, estos diseños requieren un número tan elevado de alternativas que se hace difícil su evaluación, provocando que los entrevistados no utilicen criterios compensatorios. La utilización de diseños Box-Behnken agrupados en bloques permite reducir el esfuerzo cognitivo de los entrevistados y, a la vez, ajustar un modelo de segundo grado. Este trabajo ilustra, mediante un experimento, el uso y las ventajas de utilizar diseños Box-Behnken en estudios de mercado. Los resultados obtenidos muestran el mayor rendimiento de estos modelos en comparación con los diseños factoriales habituales.AbstractConjoint analysis is a technique used to study consumer preferences in market research. One of the most important issues is to determine the choice set which respondents must assess; usually factorial designs to estimate part-worth factors have been used. But, if the researcher is also interested in estimating two or more factor interactions, factorial designs require such a large number of alternatives that makes their evaluation very difficult, leading respondents to not use compensatory criteria. Using Box-Behnken designs in blocks reduce the cognitive effort made by respondents and, at the same time, it allows fitting a quadratic model. This paper illustrates, through an experiment, the properties and how to use Box-Behnken designs in market research. Results showed a better performance of these models when compared with standard factorial designs.