New Articles

  1. Roles

    A major challenge of almost all organizations today is to find a way to integrate the knowledge and expertise of their personnel in decision making and forecasting.  In The Wisdom of Crowds , James Surowiecki shows that under certain conditions -...
  2. Politics, Governance and Control

    The ability for AHP to aggregate (synthesize) and filter (assign roles) is important for several reasons. Governance and Roles Power and control are distributed in organizations in a wide variety of ways.  An effective decision process must r...
  3. Musts vs. Wants

    Compensatory decision methodologies, such as AHP are the most effective way to prioritize alternatives.  A rational decision is one that best achieves an individual's or group's objectives -- their wants.  However, there are sometimes constraints, p...
  4. Evaluation - Top down or bottom up

    When an individual or small group derives priorities in an AHP model, they can evaluate either from the top down (from goal to objectives to alternatives) or bottom up (from alternatives, to covering objectives, to top level objectives).    A to...
  5. AIJ and AIP

    Prioritization and decision making is often performed in a group context.  There are two ways to aggregate individuals' judgments and preferences with AHP, depending on whether the group is assumed to act together as a synergistic group in achievin...
  6. Structuring

    In conformity with the second of the three AHP axioms originally proposed by Saaty, the elements of any cluster should be "homogeneous," meaning that they should differ in importance from one another by no more than an order of magnitude. This req...
  7. Redundant Judgments

    A minimum spanning set of judgments for a cluster of n elements consists of a set of n -1 judgments, in that every element can be "reached" from every other element.  It is necessary to have a spanning set of judgments in order to compute the pri...
  8. Accuracy of Derived Priorities

    The accuracy of the priorities computed from pairwise relative comparisons has been validated over the years in numerous studies.   First, it has been shown that for a pairwise comparison matrix A = [ a     ij ] that is consistent (sometimes cal...
  9. Missing Judgments

    The number of judgments in a cluster, n ( n -1) divided by 2, refers to the maximum number of pairwise comparisons in a cluster.  However, Expert Choice can compute priorities from an eigenvector equation when there are missing judgments.  At a min...
  10. Validation exercises

    Brightness of Light Experiment Area Validation Experiment The relative areas of different geometric shapes (each within an order of magnitude) were derived from pairwise verbal judgments for shapes such as the following:  This experiment...