Suchergebnisse

The sequence of items on a questionnaire or interview schedule may influence the nature of response; such order effects have both positive & negative aspects. A method is proposed for testing & controlling these order effects, while preserving the positive aspects of question sequencing. The method is based on the theory of randomization & the availability of highly flexible computer text-editing algorithms. An illustrative application of the procedure is discussed, & its impact on response rates, the coding of data, the development of personalized research materials, & cost are reviewed. AA.

The purpose of this paper is to discuss some recent developments in trade‐off analysis which may provide distribution managers some guidance in (1) evaluating the physical distribution service (PDS) mix, (2) setting service levels, and (3) determining which elements of the mix warrant the greatest attention. This article proceeds by briefly discussing the new approach, and then illustrating how it might be used; the paper ends with some suggestions concerning the future use of these methods.

ABSTRACTThe physical distribution management process involves dual, but conflicting objectives: (1) the minimization of system costs and (2) the maximization of service levels. Most physical distribution research focuses on cost minimization and treats service levels as constraints. This paper, however, highlights the service aspect of distribution. It reports an experiment with purchasing agents designed to test three alternative approaches for evaluating customers' (dollar) trade‐offs between service levels received and cost. Two of the approaches indirectly derive trade‐off values; the other approach relies on directly reported trade‐off information. In this experiment all three of the approaches were quite accurate in modeling customers' preferences for different physical distribution mixes, but the indirect procedures were more accurate than the direct approach.

AbstractThis paper proposes a method, canonical rotation analysis, which facilitates the substantive interpretation of results in multivariate analysis. Canonical rotation analysis is developed as a model which integrates multivariate least squares approaches and the varimax rotation criterion. The generalized applicability of the model to canonical correlation, multiple discriminant analysis, and multivariate analysis of variance is developed. The advantages and limitations of canonical rotation analysis are discussed and illustrated in the context of an industrial marketing research problem.