Cross-Scale Attribution & Aggregation Error¶

← Back to Scale, Hierarchy & Emergence Mismatch

Evidence or explanation at one level is projected onto another, hiding subgroup heterogeneity, marginal change, contingency, or part–whole causation.

84 mechanisms across 10 solution archetypes. This is a recurring problem pattern within Scale, Hierarchy & Emergence Mismatch; the mechanisms below inherit it from the primary archetype they instantiate.

Because this set contains more than 30 mechanisms, it is divided by form family—the concrete kind of thing a practitioner deploys, enacts, maintains, or convenes. This is a browsing subdivision only; it does not change the inherited problem classification. Click a form below to jump to its fully visible section.

Form family	Mechanisms	Description
Analysis, Modeling & Optimization	42	A calculation, model, estimator, diagnostic, comparison, simulation, or optimization that transforms inputs into an inference, prediction, recommendation, or formal result.
Assessment, Review & Assurance	13	A bounded evaluation of existing evidence, work, compliance, or readiness that produces a finding, approval, correction, or disposition.
Control, Automation & Runtime	1	A state-dependent executable mechanism that senses, triggers, schedules, filters, throttles, routes, or actuates during operation.
Decision, Gate & Allocation	1	A bounded selection, disposition, routing, admission, prioritization, matching, or allocation among eligible alternatives.
Experiment, Test & Rehearsal	2	An active probe, controlled variation, simulated condition, or practiced execution used to generate evidence or readiness.
Monitoring, Sensing & Alerting	6	Ongoing or repeated observation of actual state that emits measurements, indicators, dashboards, surveillance signals, or alerts.
Protocol, Workflow & Routine	1	A repeatable ordered sequence of actions, handoffs, states, or escalation steps, including procedures, runbooks, routines, recovery sequences, and lifecycle workflows.
Record, Log & Register	1	A durable, usually accumulating account of actual events, decisions, custody, exceptions, or state transitions whose value depends on history, provenance, or accountability.
Representation, Specification & Plan	16	A non-executable information artifact that externalizes understood, desired, or future structure, including maps, matrices, templates, checklists, specifications, reports, plans, and schedules.
Rule, Policy & Commitment	1	A standing constraint, permission, default, threshold, quota, obligation, right, or conditional action rule governing future behavior.

Analysis, Modeling & Optimization¶

A calculation, model, estimator, diagnostic, comparison, simulation, or optimization that transforms inputs into an inference, prediction, recommendation, or formal result.

42 mechanisms · View full form family

Agent-Based or Ensemble Simulation — Builds a population of heterogeneous agents from the bottom up to test whether their varied micro-behavior actually reproduces the macro equilibrium.
Aggregation Sensitivity Test — Varies the aggregation and bridge-rule assumptions to reveal how much a whole-level result is an artifact of how the parts were combined.
Bottom-Up Simulation — Executes formalized part states and interaction rules forward to see whether whole-level behavior actually emerges from the bottom up.
Cohort or Vintage Analysis — Compares entering groups by common start period, design, supplier, policy, or exposure at equivalent maturity.
Comparative-Case Attribution Test — Uses real cases where the actor varied under similar structures, or the structure varied under similar actors, as natural experiments that discriminate among competing attributions.
Composition-vs-Transformation Dashboard — Displays how much of an aggregate shift is composition versus within-unit transformation and routes the decision to the matching intervention lever.
Contribution Waterfall Decomposition — Reconciles aggregate change to legacy stock, entering contribution, exits, mix, price, base, and residual effects.
Counterfactual Actor-Substitution Probe — Holds the structure fixed and asks what a plausible substitute, an absence, or a delay of the focal actor would have changed — bounding how replaceable the person really was.
Counterfactual Sensitivity Matrix — Scores a set of alternative branches on fixed dimensions — plausibility, evidence support, scale-boundedness, and outcome-relevance — to separate the load-bearing counterfactuals from the merely vivid ones.
Covariance Selection-Term Calculation — Isolates the selection channel by computing the covariance between a unit's value and its change in relative weight — a single statistic whose sign says whether high-value units gained share.
Crossover Scenario Projection — Projects a conditional range for aggregate flattening, convergence, or reversal under alternative contribution and turnover scenarios.
Decomposition Residual Reconciliation Workflow — Takes the leftover after selection and transmission are subtracted from the observed change and attributes it to unmatched units, scale drift, or normalization rather than substance.
Ecological Scale Mapping — Maps nested spatial scales — organism, patch, watershed, region — and traces how a local ecological event travels outward along the physical flows that connect them.
Entry/Exit Normalization Protocol — Fixes how entrants and exiters enter the weights so that churn in the population does not masquerade as real change in the weighted mean.
First-Difference or Derivative Estimate — Estimates directional change from discrete differences or a continuous derivative approximation.
Interaction Graph Analysis — Maps which parts act on which as a network of nodes and interaction edges, so the relational structure behind a whole-level pattern becomes visible.
Lineage or Panel Correspondence Matrix — Maps which units in the first state correspond to which in the second — continuing, entered, exited, split, or merged — so selection and transmission can be told apart at all.
Local / Global Analysis — Contrasts local cases, subgroups, or sites with aggregate system behavior so local variation and global trends can be interpreted together rather than confused.
Local-to-Global Risk Map — Charts how many small, individually-tolerable local exposures aggregate up a shared channel until, at some threshold, the risk changes form and becomes systemic.
Mesoscale Simulation — Models intermediate units — cells, cohorts, corridors, patches — where behavior lives that both micro-detail and macro-averages miss, and runs them forward to check it.
Micro / Meso / Macro Analysis — Compares individual or unit-level evidence, intermediate organizational or network patterns, and broad system-level behavior to locate the level at which the decisive pattern appears.
Multi-Level Policy Analysis — Follows a single rule downward through each governance layer to see how its intent turns into local incentive and behavior — then picks the layer where the rule should actually be set.
Multilevel Modeling Review — Reviews whether a nested-data claim needs partial pooling — borrowing strength across groups so small subgroups are neither over-trusted nor erased.
Network and Institutional Position Map — Charts positions, authority, brokerage, and selection in the relational structure to show which options a role afforded and how replaceable its occupant was.
Organizational Level Analysis — Reframes workplace problems across individual, role, team, process, unit, enterprise, and ecosystem levels to avoid assigning causes at the wrong layer.
Organizational Level Mapping — Traces how a local workaround aggregates upward into an enterprise-level pattern, and how enterprise metrics press back down on the front line — through the incentives that connect the two.
Organizational Unit Model — Represents an organization at the team-or-unit scale so coordination behavior that individual logs and company averages both hide becomes visible.
Paired Micro/Macro Case Study — Analyzes one phenomenon twice — as a close case narrative and as an aggregated structural account — then produces an explicit ledger of what each resolution reveals and hides.
Policy-Scale Analysis — Reasons at population or institutional scale for public decisions while validating that the aggregate does not erase subgroup harms, escalating to finer review where it might.
Poststratification or Reweighting — Corrects an aggregate whose sample composition differs from the target population by reweighting subgroups to a declared, auditable population basis.
Price Equation Decomposition Table — Lays out every unit's weight and value in both states as a ledger and recomposes the weighted-mean change into an exact selection term plus a transmission term.
Process Tracing Across Levels — Reconstructs the causal chain by which a single decision propagates upward through individual, group, organizational, and institutional levels to the macro outcome, testing each link against the evidence it would have to leave.
Rolling Marginal-Contribution Curve — Estimates leading-edge direction by smoothing a declared sequence of entering units, cohorts, or periods.
Selection–Transmission Sensitivity Analysis — Re-runs the selection–transmission split under alternative windows, unit definitions, and weighting schemes to report how stable the verdict is before it drives a decision.
Sensitivity Analysis by Group — Re-runs the aggregate under alternative groupings, weights, windows, and exclusions to see whether the conclusion survives the choices that produced it.
Simpson's Paradox Check — Tests whether an aggregate relationship reverses or materially changes once a confounder or composition variable is conditioned on — the fingerprint of a Simpson reversal.
Stratified Analysis Protocol — Splits an aggregate into pre-declared strata and compares each subgroup's pattern against the pooled figure, so hidden heterogeneity surfaces before the claim is trusted.
Structural-Constraint Relaxation Probe — Holds the actor fixed and loosens or tightens one structural condition at a time to see whether the actor's effect survives the change — measuring how conditional that effect really was.
System-of-Systems Causal Mapping — Maps a whole assembled from autonomous subsystems that are themselves complex, tracing how influence crosses their engineered interfaces to produce — and sometimes cascade into — whole-system behavior.
Variance Decomposition Table — Splits the spread hidden beneath an equilibrium into named sources — within-group, between-group, temporal, measurement — so you can see what kind of heterogeneity it is.
Within-Unit Change Assay — Measures the transmission channel directly by pairing each continuing unit's before and after value and averaging the within-unit change, ignoring composition entirely.
Zoom-In / Zoom-Out Diagnosis — Deliberately narrows and widens the view of a problem, using each movement to ask what becomes visible, invisible, overemphasized, or actionable.

Assessment, Review & Assurance¶

A bounded evaluation of existing evidence, work, compliance, or readiness that produces a finding, approval, correction, or disposition.

13 mechanisms · View full form family

Cross-Scale Impact Review — A checklist-style review that takes a proposed action and asks, at the level above and the level below the target, whether it quietly shifts burden onto them.
Ecological Scale Review — Reads the characteristic scale off ecological evidence spanning organism, patch, habitat, landscape, watershed, and biome, so interventions target the scale where the process is actually generated, and marks the boundary where that process's dynamics no longer hold.
Mix-Shift and Base-Effect Audit — Tests whether composition, denominator, price, seasonality, selection, or comparison base creates apparent divergence.
Narrative Focal-Actor Audit — Compares how much of the record an actor occupies against how much causal evidence actually supports them, surfacing archive and commemoration bias and the contributors the record erased.
Paired Confidence-Band Review — Reviews uncertainty in both trajectories and in their directional relationship, including shared-data dependence.
Plural Causal Synthesis Review — Holds several competing causal models open at once, restates the scoped target, and publishes a bounded, versioned synthesis that separates causal contribution from praise and blame.
Representative Microcase Panel — Pulls a deliberate spread of individual cases across the distribution so humans can read how the equilibrium is actually experienced.
Representativeness and Nonresponse Review — Checks whether differential participation or missingness has skewed the aggregate away from the population it claims to describe, and bounds the claim accordingly.
Residual Explanation Review — Reviews what the part-level account failed to explain and decides whether the residual is emergent, contextual, or a cue to escape reduction.
Scale-Shift Review Prompt — A fixed question set run against a finished claim to ask what becomes visible, invisible, exaggerated, or smoothed when the analysis is deliberately shifted a scale finer or coarser.
Scale-Specific Policy Analysis — Evaluates whether a policy problem and its intervention point sit at the person, program, institution, region, or system level.
Stratified Sampling Review — Audits whether the measurement behind an aggregate actually covers every relevant subgroup and locality, rather than over-weighting the easiest cases to observe.
Turning-Point Opportunity Analysis — Tests whether a narrow option window or an inherited path made one decision unusually consequential, and how quickly the window opened and closed.

Control, Automation & Runtime¶

A state-dependent executable mechanism that senses, triggers, schedules, filters, throttles, routes, or actuates during operation.

1 mechanism · View full form family

Level-of-Detail Model — Maintains several fidelities of the same system at once and switches between them as the purpose demands, bringing detail back the moment it starts to matter.

Decision, Gate & Allocation¶

A bounded selection, disposition, routing, admission, prioritization, matching, or allocation among eligible alternatives.

1 mechanism · View full form family

Ecological Scale Selection — Finds the ecological unit — patch, watershed, landscape — at which a process actually operates by testing candidate scales and seeing where the pattern is sharpest.

Experiment, Test & Rehearsal¶

An active probe, controlled variation, simulated condition, or practiced execution used to generate evidence or readiness.

2 mechanisms · View full form family

Ablation or Knockout Test — Removes or disables a part and checks whether the whole-level behavior breaks, isolating which constituents are actually necessary.
Equilibrium Stress Test — Shocks the composition and conditions beneath an equilibrium to see whether the aggregate stability actually survives distributional change.

Monitoring, Sensing & Alerting¶

Ongoing or repeated observation of actual state that emits measurements, indicators, dashboards, surveillance signals, or alerts.

6 mechanisms · View full form family

Aggregate–Marginal Sign-Divergence Alert — Opens review when linked aggregate and contribution trajectories meet sign, persistence, materiality, uncertainty, and quality conditions.
Cumulative-versus-Incremental Dashboard — Places accumulated aggregate state, the leading-edge trajectory, uncertainty, maturity, divergence duration, and the crossover horizon on one governed surface that refuses to treat either measure as primary.
Distributional Dashboard — Puts the aggregate indicator and its full distribution on one live surface, so an equilibrium is never read as a single average.
Subgroup Dashboard with Warning Flags — Shows aggregate and subgroup figures side by side with rules that flag masked harm, unstable small cells, and equity-relevant gaps as they arise.
Subgroup Excursion Alert — Fires when a subgroup or locality breaches a preset threshold, even while the population mean stays flat.
User-Level / System-Level Analytics Comparison — Compares individual user journeys, segment behavior, cohort patterns, and aggregate platform metrics to reveal product or service problems hidden by a single analytic level.

Protocol, Workflow & Routine¶

A repeatable ordered sequence of actions, handoffs, states, or escalation steps, including procedures, runbooks, routines, recovery sequences, and lifecycle workflows.

1 mechanism · View full form family

Branch-Pruning Protocol — Runs proposed counterfactual branches through ordered exclusion gates, cutting the ones that need too many unsupported changes, breach a documented constraint, or rewrite a commitment the path had already locked.

Record, Log & Register¶

A durable, usually accumulating account of actual events, decisions, custody, exceptions, or state transitions whose value depends on history, provenance, or accountability.

1 mechanism · View full form family

Dual-Metric Decision Memo — Records aggregate-state obligations, leading-edge action, horizon assumptions, owners, resources, triggers, and review date together.

Representation, Specification & Plan¶

A non-executable information artifact that externalizes understood, desired, or future structure, including maps, matrices, templates, checklists, specifications, reports, plans, and schedules.

16 mechanisms · View full form family

Actor-Constraint Map — Reconstructs the options, beliefs, resources, pressures, and prohibitions a specific actor faced at the moment a choice was open, so 'they could have done otherwise' is judged against the real menu, not the hindsight one.
Actor–Structure Evidence Matrix — Arrays every actor action against every structural condition in one grid, forcing each cell to carry dated evidence, a causal role, and an effect so that unsupported claims and empty cells become visible.
Aggregate Trend Overlay — Superimposes a close-grained event trace on the broad distribution or trend it belongs to, so the gap between them exposes what aggregation smoothed away.
Architecture-Level Model — Fixes the scale of a software system at components and their interfaces — the right level for structural reasoning, where source lines are too fine.
Coarse-Grained Model — The representation itself — many lower-level elements collapsed into larger units or summary states at a deliberately chosen coarse scale.
Executive-Level Summary — Keeps only the variables a leadership decision could turn on and drops the operational detail that would not change it — with a note on what was suppressed.
Hinge-Point Timeline — Plots a path's decisions, accidents, and near-misses on one time axis and marks the hinges — the few moments where the outcome could plausibly have swung the other way.
Interpretive Weighting Memo — States on the record how the final account distributes explanatory weight across contingency and structure, agency and constraint, close evidence and aggregate pattern — so the interpreter's thumb on the scale is visible and contestable.
Mechanism Chain Diagram — Traces a single directed chain from a triggering part-event to the whole-level outcome, asserting that these linked steps are what produce it.
Micro-Macro Crosswalk — A one-page rule that maps individual and local states to the aggregate indicator and marks which claim is valid at which level.
Micro/Meso/Macro Causal Map — Lays one problem out on three labeled tiers — individual, group, and whole-system — and draws the causal arrows running both up and down between them.
Nested Scale Timeline — Stacks a fast micro sequence inside a meso band and a long-run macro band on aligned time axes, so a moment-by-moment episode can be read against the slow conditions that contained it.
Paired Micro/Macro Timeline — Runs a micro timeline of dated actor events beside a macro timeline of slow structural change so that contingency and pattern can be read against each other and an actor's timing role becomes visible.
Part Inventory Matrix — Lays out the whole's constituents and their state variables in a structured table, giving a reduction its parts before any interaction is claimed.
Scope Clause and Exception Note — Documents the level, scope, and known exceptions under which a part-level explanation remains valid for downstream users.
Source Resolution Table — Catalogs each source by the analytical resolution it can actually support, so evidence is matched to the scale of the question instead of stretched across it.

Rule, Policy & Commitment¶

A standing constraint, permission, default, threshold, quota, obligation, right, or conditional action rule governing future behavior.

1 mechanism · View full form family

Ecological Fallacy Guardrail — Blocks group-level statistics from being read as individual-level claims by fixing the unit of analysis and the boundary of what the aggregate is allowed to mean.