Analytical study and conclusion
Analysis question, population, method, result, limitations and recommendation. A report shows results but does not replace the justification of the conclusion.
Bundle → Layer → Finding → Questions Filled
3 bundles · 4 layers · 5 findings · 11 questions
Question and population What the study asks and about whom.
Study design
The question, population, sample and exclusions.
Analysis question
The question and the decision it supports.
- Which question does the study answer, and for which decision?
- Which population does the conclusion intend to cover?
Sample and exclusions
How data was selected and what was left out.
- How was the sample drawn, and which records were excluded and why?
- Is the sample biased relative to the population?
Method and findings How the analysis was done and what it found.
Method
The analysis method and its assumptions.
Method and assumptions
Method used, with assumptions separated from observations.
- Which method was used, on which dataset versions?
- Which statements are assumptions rather than observations?
Findings
Results with their scope and limitations.
Analytical finding
A result with scope, uncertainty and limitations.
- What is the scope of applicability of the finding?
- Does the finding claim causation from correlation?
- Which alternative interpretations were considered?
Recommendation What the study proposes and what happened to it.
Recommendation and decision
A proposal kept separate from a decision.
Recommendation
A proposal linked to findings and to any decision taken.
- Which findings support the recommendation?
- Was the recommendation adopted, and by whom?
Classifiers Filled
- Family
- Enterprise profiles
- Category
- Enterprise subject
- Entry kind
- subject
- Domain
- EnterpriseDAT
- Industry
- Cross-industry
- Tags
- EM-DAT-07W2subjectAnalyticalStudyAnalysisMethodAnalyticalFindingRecommendation
What it is Filled
Analysis question, population, method, result, limitations and recommendation. A report shows results but does not replace the justification of the conclusion.
Why it exists Filled
Analysis question, population, method, result, limitations and recommendation. A report shows results but does not replace the justification of the conclusion.
Distinguishing features Filled
- Every conclusion carries its scope of applicability and its limitations.
- Assumptions are recorded separately from observations.
- A recommendation stays a proposal until someone adopts it as a decision.
- Distinct from a report, which displays results but does not justify a conclusion.
What robots and AI may and may not do Filled
Must not
- Use a chart of ticket growth as proof that an employee's productivity dropped.
- State a causal claim from correlation alone.
- Record a recommendation as an adopted decision.
- Drop limitations or exclusions when summarising findings.
Only with a human decision
- Acting on findings that concern individual employees or customers.
- Adopting a recommendation as a decision.
May
- Document question, sample, exclusions, method and limitations of an analysis.
- Present alternative interpretations of the same data.
- Link a recommendation to the decision that adopted or rejected it.
Moral aspects Filled
- Analyses used to judge individuals can be unfair when samples or causal claims are weak.
- Overconfident conclusions shift risk onto those affected by the decisions.
Who is affected
- Employees and customers described by the analysis
- Decision makers
- Analysts
Owners Filled
Steward
The data owner or head of analytics who answers for data assets and their fitness for use.
Master systems
- Data catalogue
- Data warehouse
- BI platform
- Data orchestrator
Links to other meta-models Filled
neighbor
- EM-DAT-01
- EM-DAT-06
- EM-KNW-02
references
- WM-ACT-034 - conceptual-candidate
- WM-KNW-007 - conceptual-candidate
What else AI and robots need to interact with it Filled
Identity and identifiers required Filled
- Identified by study identifier, with findings and recommendations numbered within the study.
Direct properties not applicable Not applicable
Not applicable
Enterprise record contour: physical properties belong to referenced world models.
Recognition optional Filled
- A study record names a question, a sample, a method and limitations.
- Often confused with a report or dashboard showing the same figures.
Capabilities and actions required Filled
- Conclusions can be reviewed against their method and sample.
- Recommendations can be traced to decisions and outcomes.
Hazards and failure modes required Filled
- False causal claims that drive harmful decisions.
- Hidden sample bias that limits where conclusions hold.
- Recommendations treated as decisions without accountability.
Standards and interfaces required Filled
- W3C PROV-O for provenance of findings.
- W3C DCAT for referencing the datasets used.
Context of use required Filled
- Used in business analysis, research and evaluation of policies or products.
- Analyses about individuals are subject to data protection and labour law.
Sources Filled
- W3C DCAT: dataset, distribution, catalog
- W3C PROV and Data Cube: provenance and observation
- SDMX and BI/data catalog practice: indicators, breakdowns, definitions and releases
- W3C PROV-O: The PROV Ontology - Checked live (HTTP 200) on 2026-10-07.
- W3C The RDF Data Cube Vocabulary - Checked live (HTTP 200) on 2026-10-07.
- SDMX: Statistical Data and Metadata eXchange - Checked live (HTTP 200) on 2026-10-07.
Open questions
- When is correlation mistakenly interpreted as causation?
- How to record the sample and exclusions?
- How to link a recommendation to a decision?
- Установить границу и решение reuse/extend/new по действующим спецификациям.
- Подтвердить semantic crosswalk, права и source mastership.
- Выбрать immutable refs; провести проверки fixtures до заявления о публикационной готовности.
Machine files
Provenance
enterprise research programme · published-partial
Built from: enterprise/models/em-dat-07/brief.json, ver-cy/world-models/card-supplements/em-dat-07.json
Still in Russian: suggested owner, blocking decisions, vercy candidates. Translate in research/enterprise/i18n/units.en.json.