Shirland, Larry E.; Jesse, Richard R. (1997, ASQ) University of Vermont, Burlington, VT
This article is available for FREE to ASQ members with the appropriate membership type and/or magazine subscriptions. If you are signed-in you should be able to download articles you are entitled to receive. If you have questions about your membership please contact Customer Care at 800-248-1946 or firstname.lastname@example.org
Comparative attribute analysis (CAA) is a technique for determining priority weights in quality function deployment (QFD) studies. QFD transforms customer needs or attributes into product requirements and specifications, and CAA can help identify the relative values of the attributes. CAA analysis involves pairwise comparisons of n attributes on a nine-point scale, with 1 corresponding to no preference between the pair and 9 corresponding to extreme preference for the second attribute in a given pair. Determining the priority weights is a problem in goal programming for which the constraints have the form wk - wj = 0, where wk and wj are the weights for pairs (j,k) of the n attributes. This paper provides an example using five attributes and ten pairs of comparisons. Two customers rate the ten pairs, producing a matrix from which the goal programming model can be built. A degree of consensus emerges from the model, based on four factors: number of attributes, number of customer raters, priority weights from each rater, and combined priority weights from all raters. An alternative to the CAA method is the analytic hierarchy process (AHP). It generates eigenvectors from the customer ratings. The AHP method has the advantage of producing hierarchies, but the CAA approach is more accurate than AHP.
Customer and market focus,Standards and specifications,Product development