AO-12 Multi-criteria decision analysis (MCDA)
Scores options against several weighted criteria, producing weights, scores and a ranking, with a test of how the ranking changes when weights change.
What it does
Scores options against several weighted criteria. Artefact: weights, scores and a ranking; test how the ranking changes when weights change.
When to use it
Use when a user must choose among options that differ on several criteria and some of them cannot be priced.
When it does not fit
Weights are arbitrary and the ranking reverses when they vary.
Result format
The result is a matrix with one row per option and one column per weighted criterion, with the weights stated and a score in each cell. It ends with a ranking of the options, a note of how the ranking changes when the weights change, and a list of the assumptions behind the weights and scores.
Requirements on the material
| Property | Requirement type | Requirement |
|---|---|---|
| Content type | Always applies | requires=text; requires=tabular |
| Unit of analysis | Always applies | requires=topic |
| Variable types | Raises a warning | prefers=ordinal; prefers=interval |
| Appraises source credibility | Applies in some cases | no |
Not restricted on: Structure, Time structure, How the sample was chosen, Level of detail available, Number of sources, Whether sources can be joined, Amount of material, Known data problems, Producer interest, Source dependence, Origin, Document genre, Language, Personal information, Security classification, Licence.
| Minimum material | At least two options, at least two criteria, and weights and scores from decision makers or experts. Weights are elicited, not found. |
|---|---|
| Additional sources needed | none |
| Not for (rules) | none |
| Not for (text) | Wrong choice when weights are arbitrary and the ranking reverses when they vary. Simple weighting and scoring is discouraged unless facilitated. |
Choosing and ordering
| Kind of technique | Primary technique, runs in step 5.3 |
|---|---|
| Phase tag | analyse |
| Other phase tags | conclude |
| Kind of finding | option ranking |
| Question answered | which option |
| Strongest statement it supports | describe |
| Needs as input |
|
| Makes as output |
|
| Must exist first | None |
| Loop target | return to gather |
Library checks by stakes
Each stakes level includes the checks of the level below it. Checks that need a person apply at high stakes only, so the process leaves them out at lower stakes (decision 38). Repeatability: judgement dependent.
| Stakes | Check | Person involved | Counts as a different method |
|---|---|---|---|
| exploratory | assumption and limitation statement | none | no |
| decision-informing | assumption and limitation statement | none | no |
| decision-informing | sensitivity analysis | none | no |
| decision-informing | code execution for arithmetic | none | no |
| high-stakes | assumption and limitation statement | none | no |
| high-stakes | sensitivity analysis | none | no |
| high-stakes | code execution for arithmetic | none | no |
| high-stakes | second technique with different assumptions | none | conditional |
| high-stakes | independent review | needed | no |
Failure modes and limits
| Model suitability | human judgement required |
|---|---|
| Typical model failure | Invents weights and scores with false precision and does not show that the ranking changes when weights change. |
| Error sources | input data; coder or rater judgement; expert opinion |
| Certainty limits | Certainty drops when the ranking reverses under other plausible weights (inconsistency), when scorers share one view (risk of bias), and when weights were set after the options were known. |
Related techniques
- should follow AO-09 Longlist-to-shortlist options analysis (options appraisal): a shortlist keeps the number of options that need scoring small
- pairs with AO-10 Cost-benefit analysis: criteria that can be monetised are better valued in money than scored
Evidence and tag basis
Documented. One family member, the analytic hierarchy process, is called controversial in the MCDA community; the Green Book accepts facilitated MCDA but advises against simple weighting and scoring. (Wikipedia, Multiple-criteria decision analysis; HM Treasury, The Green Book 2020)
Tag basis: input profile inference; selection inference; sequencing inference; robustness inference. All tag values are inference unless a source is named.