Equal weights
AvailableDawes and Corrigan (1974)
The idea
Five smartphone criteria: the unit total 1 is divided by n = 5, so every criterion receives w = 1/5 = 0.2000 regardless of its column values.
Show as table
| Criterion | Weight w |
|---|---|
| C1 | 0.2000 |
| C2 | 0.2000 |
| C3 | 0.2000 |
| C4 | 0.2000 |
| C5 | 0.2000 |
Data: Five alternatives, five ranked criteria (Roszkowska 2013).
Every criterion gets the same weight, 1/n.
When to use it
- No information about importance.
- As a baseline for sensitivity checks.
Algorithm
1Same weight for every criterion
Used together with
Why these pairs
- Any ranking method, as the "no weighting" scenario: Dua et al. (2024) run MARA, RAM and PIV with mean weights next to Entropy, MEREC, LOPCOW and CRITIC.
- The worked example of the EDAS origin paper uses equal weights.
Reference example
Details
Roszkowska, E. (2013). Rank Ordering Criteria Weighting Methods: a Comparative Overview. Optimum. Studia Ekonomiczne 5(65), 14-33. doi:10.15290/ose.2013.05.65.02
Table 4, column EW. The published 1/n values for n = 3 and n = 4 are reproduced exactly.
Checked by this site's test suite.
Sources
Show 6 sources
- Dawes and Corrigan (1974). Linear models in decision making. Psychological Bulletin 81(2), 95-106. doi:10.1037/h0037613Equal weights have no single inventor; Dawes & Corrigan (1974) and Einhorn & Hogarth (1975) are the classic "unit weights" references.
- Dawes & Corrigan (1974), Psychological Bulletin 81(2), 95-106 doi:10.1037/h0037613
- Einhorn & Hogarth (1975), Organizational Behavior and Human Performance 13(2), 171-192 doi:10.1016/0030-5073(75)90044-6
- Roszkowska (2013), Optimum. Studia Ekonomiczne 5(65), 14-33 doi:10.15290/ose.2013.05.65.02
- Dua, Duc, Bao & Trung (2024), EUREKA: Physics and Engineering doi:10.21303/2461-4262.2024.003171
- Keshavarz-Ghorabaee et al. (2021), Symmetry 13(4), 525 doi:10.3390/sym13040525