Skip to content

GCRI · システミックリスク管理

定量的・定性的手法

リスクアセスメント uses numbers where data support them and structured judgement where they do not. Probabilistic models, loss distributions, 専門家の意見聴取, bow-tie diagrams and risk matrices each answer different questions and fail in different ways. This page sets out how the main methods work, when each is fit for purpose, and how combining them keeps an assessment honest about what is known and what is assumed.

01登録

Quantitative and qualitative methods on the record.

02質問

Quantitative and qualitative methods: how the risk develops.

Probability, uncertainty and judgement. The dossier below sets out how the risk develops, what is measured, where the data come from, how it is modelled and who decides.

メカニズム

Models need data that fit

Frequency and severity models work where events are numerous and recorded consistently. For rare, novel or changing risks the data are thin, and a precise-looking number can carry more assumption than evidence.

メカニズム

Judgement carries biases

Experts anchor on recent events, overestimate their own precision and converge in groups. Structured elicitation reduces these effects by separating estimates, asking for ranges and scoring calibration.

メカニズム

Matrices compress information

Likelihood and consequence matrices are quick to use, but they rank risks coarsely, can reverse orderings and hide correlated losses. They suit screening, and need other methods before a major decision.

メカニズム

Methods combine through structure

Fault trees, event trees and bow-tie diagrams link causes, controls and consequences. They provide a frame into which quantitative estimates and expert judgement can be placed and checked.

03監視

Cascade and stress lab.

このテーマを追跡するためにチームが使う画面:その指標、状態、決定。名前は例であり、値はイメージです。

Cascade and stress lab

Quantitative and qualitative methods · National system · Scenario SC-40

Cascade crosses three systemsGCRI・システミックリスク管理

Interdependency graph

red: failed in scenario

Cascade sequence

  1. T+0HAZHeatwave and drought
  2. T+6hENGThermal plant derated, cooling water
  3. T+9hICTData centre on backup power
  4. T+14hWATPumping reduced, pressure loss
  5. T+20hHLTHospital water supply at risk

Service loss by system

Cascade and stress lab: the screen’s structure, terms and states for Quantitative and qualitative methods.例示の名称と説明用の値です。設計であり、記録でも稼働中のシステムでもありません。
04分野を横断して

Methods must be fit for risks that cross domains.

05手法とエビデンス

How quantitative and qualitative methods is modelled, measured and tested.

モデル、その仮定、データ、不確実性を、科学者やエンジニアが確認する形で示します。構造は公表された手法に従っています。描かれた値は例示であり、知見ではありません。

モデル、方程式、仮定

The model structure used for quantitative and qualitative methods, the assumptions it makes and how each is tested.

要素 i のリスクRi = f(Hi, Ei, Vi, Ci)ハザード、エクスポージャー、脆弱性、対処能力
年間期待損失EAL = ∑k pk · Lk年間確率 pk
結合システムxt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error
仮定作られる理由検証の方法
一つの事象の中では、ハザードとエクスポージャーは独立している損失の積分を扱いやすく保つ同時記録に当てはめたコピュラと比較
結合は動作点の近くで線形であるショックを A を通じて伝播させる線形範囲を超えて摂動を与えて比較する
脆弱性曲線は場所を越えて適用できる地域固有の曲線はめったに得られない観測された損失がある場合はそれに照らして検証
入力
来歴付きのバージョン管理されたデータセット
成果物
分布であり、単一の数値ではない
コード
モデルカードと試験とともに公開
再現
同じデータ、コード、環境、シード
標準的なリスクおよび状態空間の定式化です。挙げた前提はこの手法に典型的なもので、審査のために示しており、結果ではありません。
FAIR 原則・GO FAIR と FORCE11W3C PROV・World Wide Web Consortium不確実性の一貫した扱いに関するガイダンス・IPCCCEOS 解析即応データ・地球観測衛星委員会
06指標

何を、どの程度うまく測定しているか。

各指標には、その単位、更新頻度、背後にある出典の種類、値が持つことになるエビデンスのラベルが付いています。値は表示しません:プログラムが自らの権限のもとで値を提供します。

指標単位周期出典の種類ラベル
Risks assessed with quantitative estimatespercent of principal risks年次Assessment records報告値
Calibration of expert estimatescalibration score on seed questionsper elicitationStructured expert judgement records観測
Loss event recordscount of events with cause and amount recorded継続的Internal loss databases観測
Assessment uncertainty rangeratio of upper to lower bound評価ごとAssessment outputs推定
Controls with tested effectivenesspercent of key controls年次Control testing records報告値
Method documentation completenesspercent of assessments with method, data and assumptions recorded年次Assessment files報告値
07出典

エビデンスの出所。

名前の明示された公開データセットと機関の記録。それぞれにライセンス区分があります。合意に基づく出典は、その条件のもとでのみ使用し、再公開することはありません。

出典提供するものライセンス区分
IEC 31010 リスクアセスメント 技法Descriptions, strengths and limits of more than forty techniquesLicensed standard, purchase required
EM-DAT 国際災害データベース(CRED、ルーヴァン・カトリック大学)Disaster events with human and economic impactsFree for non-commercial use with registration
仙台防災枠組 Monitor and national disaster loss databasesPublished reporting of disaster losses against Sendai targets公開、国連の利用規約
TU Delft expert judgement databasePast structured expert judgement studies with calibration dataLicence to check
Published operational loss data consortia summariesAggregate operational loss patterns in financial servicesMembers only; public summaries (to check)
08決定

誰が決め、エビデンスが何に役立つか。

システミック・リスク Management prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

誰が決定するか質問このページが提供するエビデンス
Risk functions and analystsWhich method fits a given risk and decisionMethod selection guides; documentation standards
Boards and executivesHow much confidence to place in an assessment before acting on itUncertainty ranges; method documentation; calibration records
Regulators and supervisorsWhether an institution’s risk models are fit for the use made of themModel documentation; validation and back-testing evidence

このトピックが生み出す成果物

  • Method selection guides keyed to the question and the evidence available
  • 構造化された 専門家の意見聴取 protocols with calibration
  • Bow-tie and fault-tree templates linked to registers
  • Assessment files that record data, assumptions and ranges
09中核となる問い

What methods experts ask.

  • Is there enough relevant data to estimate probabilities, or would numbers convey a false sense of precision?
  • What kind of uncertainty dominates: randomness, lack of knowledge, or disagreement about how the system works?
  • How sensitive is the decision to the parts of the analysis that are least certain?
  • How can expert judgement be elicited so that it is transparent and less prone to bias?
10メカニズム

Kinds of uncertainty.

Aleatory

Randomness

Natural variability that persists even with perfect knowledge, such as weather from year to year. Probability handles it well.

Epistemic

Lack of knowledge

Uncertainty that more data or research could reduce. It should be shown, not hidden in a single number.

Deep

Disputed structure

Where experts disagree on models, probabilities or values. Scenarios and robust decision methods suit it better.

11手法と限界

A toolkit, matched to the problem.

  1. 01

    Statistical and probabilistic models

    Frequency analysis, extreme value methods and Bayesian inference from 確率と統計. Limits: rare events are poorly sampled, and past data may not reflect a changing system.

  2. 02

    不確実性の定量化

    不確実性の定量化とモデル検証 propagates input uncertainty through models and tests them against data. Limits: it cannot capture what the model leaves out.

  3. 03

    構造化された専門家判断

    Formal elicitation protocols that calibrate and combine expert views. Limits: time-consuming, and experts share blind spots.

  4. 04

    Qualitative assessment

    Scales, matrices and narrative analysis. Useful for communication and screening, but risk matrices can rank risks inconsistently and should not be the only tool.

12手法

どのように研究され、手法が言えないことは何か。

13Where this page’s references

Where this page’s references lead.

このページの読解の基準となる機関と文書。状態と版は変わります。各リンクは発行機関へ移動します。

14質問

質問と回答。

Are risk matrices reliable?
They are useful for screening and communication, but they rank risks coarsely and can mislead when risks are correlated or consequences are uncertain. Important decisions need methods that show ranges and dependencies.
What is structured expert judgement?
A formal process for eliciting estimates from experts, often with seed questions whose answers are known, so that each expert’s calibration and informativeness can be scored and estimates combined accordingly.
When should risk be quantified?
When data or models can support a number whose uncertainty can be stated, and when the decision needs it. Where they cannot, a well-documented qualitative assessment is more honest than a false number.
Are quantitative methods always better?
No. They are better when data and models are adequate. Where they are not, numbers can mislead, and structured qualitative methods or scenarios are more honest.
What is wrong with risk matrices?
They are simple and widely understood, but coarse scales can rank different risks equally, hide uncertainty and ignore dependence. They work best as a screening tool alongside other methods.
How should uncertainty be communicated?
With ranges, scenarios and plain statements of what is not known, so that decision-makers can see how much the conclusion depends on uncertain inputs.
報告書貢献する

このページからエビデンスを提供する。

報告書 is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.

GCRIシステミック・リスクマネジメントシナリオとストレステスト手法と技術ポートフォリオと準備度
システミック・リスクマネジメント

手法、データセット、または問いを持ち込んでください。

情報提供と問い合わせは本日から受け付けています。問い合わせには参照番号が付き、次の手順が示されます。申請、支払い、計算資源の割り当て、登録は、担当チーム、規約、審査体制が整ってから開始します。