No abstract

The authors propose and illustrate an extension of the method of Hierarchical Information Integration (HII). HII allows one to handle large numbers of attributes in conjoint tasks by designing subexperiments that include subsets of attributes. It assumes that individuals can use general attributes or decision constructs to summarize their impressions of these subsets, which could be clusters of detailed, managerially relevant attributes. The proposed extension involves the design of sub-experiments that include attributes plus summary evaluations of remaining constructs. Advantages are that subexperiments can be analyzed separately but also jointly to estimate one overall preference or choice model; a more flexible and easy task is obtained; and one can test the assumed hierarchical decision structure. The authors illustrate the approach with an application that models consumer choice of shopping center. In this application, results partially support the hierarchical structure and predictive validity. Finally, the authors discuss implications for further research.

This paper reviews methodological developments in choice modelling (CM) and the state of CM research in tourism, hospitality and leisure through a review of 43 CM studies. The paper emphasizes the theoretical and methodological advantages of Discrete Choice Analysis based on Random Utility Theory combined with state-of-the-art experimental design procedures for the gathering of Stated Preference data.

In this paper it is argued that models of consumer choice of shopping destination have included few attributes related to the selection of stores available in a shopping centre. The authors seek to develop and illustrate empirically a way to define the selection of stores in shopping centres, such that effects of various modifications to the available selection can be modelled by conjoint analysis (or stated preference of decompositional choice) methods. Profiles of hypothetical shopping centres are developed that describe the total size of centres as well as the marketing mix positionings of the individual stores within these centres. The approach is implemented in choice experiments, one on food shopping and one on shopping for clothing and shoes. Logit models are estimated and compared for these two product categories and for large versus small centres.

The method of hierarchical information integration can be applied to the study of complex decision-making processes in which preference formation is influenced by many attributes of choice alternatives. In this paper, we extend Louviere's (1984) original approach to include the modeling choice processes in addition to judgment processes. Assumptions underlying the original and our extension are discussed and the new method is applied in an analysis of residential choice behavior.

This paper outlines a study of recreational preferences designed to assess the usefulness of the method of hierarchical information integration for the study of complex decisionmaking processes which involve many potentially influential attributes. We assume that individuals who face complex decision problems initially group or classify influential attributes into subsets called decision constructs; then they rank these decision constructs into some overall preference for or choice among competing opportunities. To implement this conceptualization of individuals' cognitive processes we first measure overall preferences for recreational choice alternatives by creating separate experimental designs to study how individuals define each decision construct. Next we develop a design to integrate the decision constructs themselves so that we can observe how individuals' choices among, or preferences for, recreational opportunities change as we change how good an opportunity is with respect to each decision construct. The results of the study suggest that hierarchical information integration may be a potentially useful method to study complex decisionmaking problems of interest to planners and policy makers. Some avenues for further research are discussed. Substantively, our results indicate that natural environment and accessibility, and maintenance have the most influence on the Eindhoven sample's preferences for and choices among parks. Some heterogeneity in preferences is also observed.

The stated preference (SP) approach allows the individual features or attributes that make up a good to be valued. Experimental design to array attributes and attribute levels into choice sets is fundamental to SP. Respondents typically select one of two choice sets, along with the status quo alternative. SP has a number of advantages over other environmental valuation methods, such as orthogonality in attributes, which avoids colinearity problems of revealed preference methods. An application of SP to mouse hunting in Canada is presented.

No abstract