Outranking
PAMSSEM II: Total ranking variant
Martel, J. M., Aouni, B. · 1996
Overview
Outranking (partial ranking). Output typically preference_flow (higher value = preferred).
Strengths
- •Method-specific: Outranking (partial ranking)
Limitations
- •Assumes: Decision-maker can specify preference (p), indifference (q), and veto (v) thresholds
- •Assumes: Non-compensatory preference structure
Method assistant
Grounded explanations: it explains the method, it does not compute.
Assumptions to verify
- •Decision-maker can specify preference (p), indifference (q), and veto (v) thresholds
- •Non-compensatory preference structure
When not to use
- •Small dataset (m<3) → outranking benefit minimal
- •Compensatory preferences acceptable → simpler ranking method
Edge cases
- •See F.steps and D.parameters for PAMSSEM-II-specific edge handling. recommendation_metadata.assumptions_to_verify also lists boundary conditions.
Common pitfalls
- •Hatalı: 'PAMSSEM-II bu varsayımı kontrol etmeden uygulamak'. Doğrusu: Decision-maker can specify preference (p), indifference (q), and veto (v) thresholds
- •Hatalı: 'PAMSSEM-II bu varsayımı kontrol etmeden uygulamak'. Doğrusu: Non-compensatory preference structure
- •Hatalı: PAMSSEM-II'yi 'Small dataset (m<3) → outranking benefit minimal' durumunda kullanmak: recommendation_metadata.not_recommended_when alternatif öneriyor.
- •Hatalı: PAMSSEM-II'yi 'Compensatory preferences acceptable → simpler ranking method' durumunda kullanmak: recommendation_metadata.not_recommended_when alternatif öneriyor.
Worked example
- 1.Adım 1 (F1): Step 1: Local outranking index per criterion pair. Formül: S_{j}(A_{i},A_{l}) \in [0,1] Anchor: Martel-Aouni 1990, Sec.3 (PAMSSEM ancestor)
- 2.Adım 2 (F2): Step 2: Concordance index C(A_i,A_l) = Σ_{j: A_i≽A_l} w_j / Σ w_j. Formül: C(A_{i},A_{l}) = \dfrac{\sum_{j: A_{i}\succeq A_{l}} w_{j}}{\sum_{j=1}^{n} w_{j}} Anchor: PAMSSEM 1996, Eq.(1)
- 3.Adım 3 (F3): Step 3: Local discordance index d_j(A_i,A_l) measuring how strongly A_l beats A_i on criterion j. Formül: d_{j}(A_{i},A_{l}) = \dfrac{\max(0, C_{j}(A_{l})-C_{j}(A_{i}))}{\Delta_{j}} Anchor: PAMSSEM 1996, Eq.(2)
- 4.Adım 4 (F4): Step 4: Comprehensive outranking degree S(A_i,A_l) combining concordance and discordance. Formül: S(A_{i},A_{l}) = C(A_{i},A_{l})\prod_{\{j: d_{j}>C\}} \dfrac{1-d_{j}(A_{i},A_{l})}{1-C(A_{i},A_{l})} Anchor: PAMSSEM 1996, Eq.(3)
- 5.Adım 5 (F5): Step 5: Positive φ^+ and negative φ^- flows. Formül: \phi^{+}(A_{i}) = \sum_{l\neq i} S(A_{i},A_{l}),\quad \phi^{-}(A_{i}) = \sum_{l\neq i} S(A_{l},A_{i}) Anchor: PAMSSEM 1996, Eqs.(4)-(5)
- 6.Adım 6 (F6): Step 6: Net flow φ(A_i) = φ^+(A_i) − φ^-(A_i). Formül: \phi(A_{i}) = \phi^{+}(A_{i}) - \phi^{-}(A_{i}) Anchor: PAMSSEM 1996, Eq.(6)
- 7.Adım 7 (F7): Step 7: PAMSSEM I partial ranking from (φ^+, φ^-); PAMSSEM II full ranking from φ descending. Formül: \text{PAMSSEM I: } (\phi^{+},\phi^{-})\text{ partial};\quad \text{PAMSSEM II: rank by }\phi\text{ descending} Anchor: PAMSSEM 1996, Sec.4
Commonly paired with
- •AHP + PAMSSEM-II (high)
- •BWM + PAMSSEM-II (high)
- •ENTROPY + PAMSSEM-II (high)
- •CRITIC + PAMSSEM-II (high)
- •SWARA + PAMSSEM-II (high)
How to cite
Martel, J. M.; Aouni, B. (1996). Incorporating the decision-maker's preferences in the goal-programming model with fuzzy goal values. Journal of the Operational Research Society.