Difference between revisions of "Analytical Hierarchy Process (AHP)"

From forestDSS
Jump to: navigation, search
Line 6: Line 6:
  
 
<li>
 
<li>
1. Setting up a decision hierarchy by decomposing the decision problem into a hierarchy of interrelated elements. Each level must be linked to the next-higher level and adjacent elements within one level must not be too disparate.</li>
+
1. Setting up a decision hierarchy by decomposing the decision problem into a hierarchy of interrelated elements. Each level must be linked to the next-higher level and adjacent elements within one level must not be too disparate.
<li>2. Generating input data consisting of comparative judgement by pairwise comparisons of decision elements.</li>
+
<li>2. Generating input data consisting of comparative judgement by pairwise comparisons of decision elements.
<li>3. Synthesizing the judgments and estimate the relative weights by using the "eigenvalue" method to generate a derived ratio scale that reflects the local priorities of the elements in the hierarchy.</li>
+
<li>3. Synthesizing the judgments and estimate the relative weights by using the "eigenvalue" method to generate a derived ratio scale that reflects the local priorities of the elements in the hierarchy.
 
<li>4. Determination of the aggregate relative weights of the decision elements to arrive at a set of rating for the decision alternatives.
 
<li>4. Determination of the aggregate relative weights of the decision elements to arrive at a set of rating for the decision alternatives.
 
</li>
 
</li>

Revision as of 17:05, 22 September 2014


The Analytic Hierarchy Process (AHP) developed by Saaty (1977, 1980) is a robust and flexible multi-criteria decision analysis technique based on the prior articulation of preferences by the decision maker. It allows to analyze multi-criteria decision problems with both qualitative and quantitative aspects.

The AHP can be summarized as a four-step procedure:

  • 1. Setting up a decision hierarchy by decomposing the decision problem into a hierarchy of interrelated elements. Each level must be linked to the next-higher level and adjacent elements within one level must not be too disparate.
  • 2. Generating input data consisting of comparative judgement by pairwise comparisons of decision elements.
  • 3. Synthesizing the judgments and estimate the relative weights by using the "eigenvalue" method to generate a derived ratio scale that reflects the local priorities of the elements in the hierarchy.
  • 4. Determination of the aggregate relative weights of the decision elements to arrive at a set of rating for the decision alternatives.
  • Further references: