Policy selection by structural mapping

Abstract

Abstract The paper is concerned with the selection of ‘best’ policies from a range of alternative possibilities where each policy is assessed in terms of its degrees of attainment of a set of objectives. The method proposed is based on multi-dimensional scaling techniques as further developed by Kendall for drawing maps based on fragmentary information. In the application discussed in this paper the input information is solely a list of those pairs of policies which have consequences which are approximately equally attractive. It is shown that such information can be sufficient to draw maps of the policies in such a way that two small groups of policies appear consistently at the extremes of the maps. It is suggested that these groups should normally correspond to the ‘best’ and ‘worst’ policies. In other words, an axis of preference might be deduced solely from statements of indifference and a comparison with the utilities of the policies appears to give credence to this.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 33 citations exist upstream.