LMAW
Updated 2026-08-11
INTRODUCTION
English translation pending.
CORE DEFINITION
The Logarithm Methodology of Additive Weights (LMAW) is a criterion weighting method in which experts rank the criteria and assign scores expressing preference. A logarithmic transformation is applied to the ratios between scores, which compresses the influence of extreme values, and the transformed values are combined into additive weights and normalized to sum to one. The method's purpose is robustness: because a single very high score on one criterion would otherwise inflate its weight disproportionately, the logarithmic step dampens that effect. It assumes the expert rankings and scores are meaningful, since the transformation changes their scale but not their subjectivity.
SCAFFOLDING EFFECT
Reduce cognitive load
- Use rank then score: have experts order the criteria before assigning any numeric preference values. - Use log compression: transform the score ratios so one extreme rating cannot dominate the weight vector. - Use cross-method check: compare the weights against another weighting method and investigate disagreements.
Anchor fast decisions
Weighting methods that work directly with raw expert scores are sensitive to outliers, because a criterion rated far above the rest absorbs most of the weight. A logarithmic transformation compresses large ratios more than small ones, so differences at the high end translate into smaller weight differences than they otherwise would. The additive aggregation keeps the weighting transparent enough to explain to the experts who supplied the judgments. The transformation improves stability but cannot correct for a ranking that was wrong to begin with.
MINIMUM ACTION
In progress 0/1Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- doi.orghttps://doi.org/10.22190/fume210214031pverified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS