Data Envelopment Analysis / DEA
Updated 2026-08-13
INTRODUCTION
English translation pending.
CORE DEFINITION
Data envelopment analysis uses linear programming to estimate a best-practice efficiency frontier for a set of comparable decision-making units that consume multiple inputs and produce multiple outputs, without requiring an assumed functional form. Each unit receives a relative efficiency score by comparison with the frontier, and slack variables indicate how much input could be reduced or output increased to reach it. The core claim is that when no absolute standard exists, comparison among peers still identifies a frontier and points laggards toward specific improvements. The qualification is that results depend entirely on the chosen inputs and outputs, and efficiency is relative to this sample rather than absolute.
SCAFFOLDING EFFECT
Reduce cognitive load
- Choose the measures: select the inputs and outputs that represent the unit's real work. - Score the units: compute each unit's relative efficiency against the estimated frontier. - Read the slacks: use the input and output gaps to specify concrete improvements.
Anchor fast decisions
Efficiency requires a standard, and where no engineering standard exists, the best observed combinations of inputs and outputs supply one. Enclosing the observed units in a frontier identifies which combinations are not dominated, and the distance from that frontier measures how much a unit could improve without any assumption about the underlying production function. Slack variables then translate the distance into specific directions, such as which input to cut. Because the frontier is built from the sample, adding a better unit shifts it and changes everyone's score.
MINIMUM ACTION
In progress 0/1Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- en.wikipedia.orghttps://en.wikipedia.org/wiki/Data_envelopment_analysisverified
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