HierarchicalDEA-CCR-SMAA_ranks

Provider:PUT
Version:1.0

Description

Computes ranks for the given DMUs (alternatives) using SMAA-D method and CCR Data Envelopment Analysis Model with hierarchical structure of outputs. For given number of samples returns a matrix with alternatives in each row and rankings in each column. Single cell indicates how many samples of respective alternative gave respective position in ranking.

Inputs

(For outputs, see below)

units

Description:

A list of alternatives (DMUs).

performance

Description:

A list of alternatives (DMUs) performances (on leaf hierarchy criteria).

XMCDA related:

  • Tag: performanceTable

  • Code:

    <performanceTable>
                                    <alternativePerformances>
                                            <alternativeID> [...] </alternativeID>
                                            <performance>
                                                    <criterionID>
                                                            [...]
                                                    </criterionID>
                                                    <value>[...]</value>
                                            </performance>
                                            [...]
                                    </alternativePerformances>
                                    [...]
                            </performanceTable>
    

hierarchy

Description:

The hierarchical structure of criteria.

XMCDA related:

  • Tag: hierarchy

  • Code:

    <hierarchy>
        <node>
            <criterionID>[...]</criterionID>
            <node>
                <criterionID>[...]</criterionID>
                <node>
                    [...]
                </node>
                [...]
            </node>
            [...]
        </node>
    </hierarchy>
    

weights constraints

Optional: yes, disabled by default

Description:

A list of hierarchy criteria linear constraints.

XMCDA related:

  • Tag: criteriaLinearConstraints

  • Code:

    <criteriaLinearConstraints>
                                    <constraint>
                                            <element>
                                                    <criterionID> [...] </criterionID>
                                                    <coefficient>
                                                            [...]
                                                    </coefficient>
                                            </element>
                                            [...]
                                            <operator>[...]</operator>
                                            <rhs>
                                                    [...]
                                            </rhs>
                                    </constraint>
                                    [...]
                            </criteriaLinearConstraints>
    

parameters

Description:

“number of samples” represents the number of samples to generate; “hierarchy node” is the ID of the hierarchy criterion for which the analysis should be performed.

GUI information:

  • Parameter values can be defined via the GUI or the XMCDA file, by default via GUI.
  • Name: number of samples
    • Constraint description: The value should be a positive integer.
    • Type: integer
    • Default value: 100
  • Name: hierarchy node
    • Type: string
    • Default value: “root”
  • Name: random seed (-1 for default time-based seed)
    • Constraint description: The value should be a non-negative integer or -1 if no constant seed required.
    • Type: integer
    • Default value: -1

XMCDA related:

  • Tag: methodParameters

  • Code:

     <methodParameters>
        <parameter id="samplesNb">
            <value><integer>%1</integer></value>
        </parameter>
        <parameter id="hierarchyNode">
            <value><label>%3</label></value>
        </parameter>
        <parameter id="randomSeed">
            <value><integer>%4</integer></value>
        </parameter>
    </methodParameters>
    

Outputs

rank acceptability indices

Description:

A performance table for given alternatives. Single performance consists of attribute criterionID representing certain ranking, and a value representing ratio of samples attaining this ranking.

XMCDA related:

  • Tag: performanceTable

  • Code:

    <performanceTable>
                                    <alternativePerformances>
                                            <alternativeID> [...] </alternativeID>
                                            <performance>
                                                    <criterionID> Rank [...]</criterionID>
                                                            <value>
                                                            [...]
                                                            </value>
                                            </performance>
                                            [...]
                                    </alternativePerformances>
                            </performanceTable>
    

average rank

Description:

A list of alternatives with average rank (obtained with sampling).

XMCDA related:

  • Tag: alternativesValues

  • Code:

    <alternativesValues>
                                    <alternativeValue>
                                      <alternativeID> [...] </alternativeID>
                                      <values>
                                              <value>
    [...]
    </value>
                                      </values>
                                    </alternativeValue>
                                    [...]
                            </alternativesValues>
    

messages

Description:

A list of messages generated by the algorithm.

XMCDA related:

  • Tag: methodMessages

For further technical details on the web service underlying this program, have a look at its documentation here.