Simulation Result Dashboard¶
Metric or dashboard — instantiates Monte Carlo Uncertainty Exploration
Communicates outcome distributions, key percentiles, risk thresholds, and sensitivity summaries to stakeholders.
Simulation Result Dashboard computes nothing new; it is the presentation layer that makes a simulation's results legible to people who will never open the model. Its identity is communication, not analysis: it takes the outcome distribution, the key metrics, the individual scenarios, and the sensitivity ranking that other mechanisms produced, and renders them so a stakeholder can read the shape of the uncertainty, find the percentile that governs their decision, see the probability of crossing a threshold, and understand which inputs drive the result — all at a glance. Everything distinctive about it is a display choice: what to show, what to hide, how to keep the picture honest about the uncertainty behind it. Done well it turns a distribution into a decision; done badly it launders simulation noise into false confidence.
Example¶
A city transit authority has simulated the cost of a light-rail extension, and the board must vote on a budget. The raw output is a distribution over hundreds of thousands of runs — useless to a room of elected officials. The dashboard renders it: a cost curve with the median and the 80th/95th percentiles marked, a single prominent number for the probability of exceeding the approved budget (34%), a "worst credible case" panel that opens one inspectable tail scenario (a tunneling delay stacking on a steel-price spike), and a short sensitivity bar showing that tunneling risk drives most of the spread. The board does not debate the model; it debates the 34% and decides to add contingency to the one driver the sensitivity bar highlighted. The dashboard's value was entirely in framing — the same runs, shown as a bare mean, would have hidden every one of those facts.
How it works¶
- Render the distribution, not the mean. Show the full outcome shape with its spread and skew, so the audience sees the range rather than a single deceptive average.
- Surface the governing metrics. Foreground the specific percentiles and threshold-crossing probabilities the decision turns on, rather than a wall of statistics.
- Provide a window into cases. Let users open a representative or tail scenario to ground the abstraction in a concrete story.
- Summarize the drivers. Present the sensitivity ranking compactly so the audience knows which uncertainties are worth their attention.
- Preserve honesty markers. Keep sampling error, assumption caveats, and convergence status visible so precision is not mistaken for certainty.
Tuning parameters¶
- Metric prominence — which numbers get headline treatment. Elevating the decision-relevant percentile focuses the audience; elevating the mean quietly misleads.
- Distribution vs. point framing — how strongly the full shape is shown against summary numbers. Richer shape is more honest but less immediately digestible.
- Uncertainty disclosure — whether error bands, caveats, and convergence status are shown or suppressed for a cleaner look. Cleaner almost always means less honest.
- Interactivity depth — how far users can drill into scenarios and re-slice. More depth serves analysts but can overwhelm executives.
- Audience tailoring — the same runs rendered for a board vs. a modeling team, trading simplicity against completeness.
When it helps, and when it misleads¶
Its strength is leverage: a well-designed dashboard is what actually moves a decision, because it makes distribution, threshold risk, and drivers comprehensible to non-modelers in one view, and it can enforce honesty by refusing to show a mean without its spread.
Its failure mode is that polish is persuasive independent of validity — a crisp chart of a garbage simulation is more dangerous than the garbage alone, because it lends the number an authority the assumptions never earned. This is the McNamara fallacy at the interface: what is easily displayed and quantified crowds out what matters but resists a clean number.[n1] The classic misuse is a beautiful single-point or mean-only display that hides the uncertainty entirely. The guarding discipline is to make the dashboard always carry its uncertainty markers — spread, sampling error, and assumption caveats — and to treat "how certain is this?" as a first-class element of the view rather than fine print.
How it implements the components¶
outcome_distribution— renders the full simulated shape, spread, and skew rather than collapsing to a summary.decision_metric— foregrounds the governing percentiles and threshold-crossing probabilities the audience must act on.scenario_inspection_view— offers a window into representative and tail cases produced upstream, grounding the abstraction.sensitivity_partition— displays the driver ranking compactly so attention lands on the inputs that matter.
It computes none of these — it consumes them. It does not run the draw loop (random_sampling_rule, convergence_diagnostic — Monte Carlo Simulation Method) nor build the model (simulation_model — Uncertainty Propagation Model); it is strictly the display of what those produce.
Related¶
- Instantiates: Monte Carlo Uncertainty Exploration — the archetype's communication surface.
- Consumes: Monte Carlo Simulation Method (the outcome distribution), Probabilistic Risk Simulation (threshold probabilities), and Stochastic Sensitivity Analysis (the driver ranking).
- Sibling mechanisms: Monte Carlo Simulation Method · Uncertainty Propagation Model · Probabilistic Risk Simulation · Scenario Sampling Workflow · Stochastic Sensitivity Analysis · Portfolio Risk Simulation · Operational Capacity Simulation
Editorial Notes¶
Form Classification¶
Form family: Interface, Display & Cue
Rationale: Simulation Result Dashboard operates as a user-facing prompt, display, template, or perceptual cue that shapes attention and action at the point of use because it communicates outcome distributions, key percentiles, risk thresholds, and sensitivity summaries to stakeholders.
Independent corroboration: The frozen evidence defines Simulation Result Dashboard as 'Communicates outcome distributions, key percentiles, risk thresholds, and sensitivity summaries to stakeholders', so its operative form is Interface, Display & Cue.
Nearest alternative: Representation, Specification & Plan — Simulation Result Dashboard includes features of a static representation, map, specification, schema, or prospective plan that externalizes information, but its defining operation is a user-facing prompt, display, template, or perceptual cue that shapes attention and action at the point of use.
Review outcome: Independent reviewer agreement; medium confidence.
Origin Attribution¶
Primary origin: Data Science & Analytics
Origin pattern: Cross-disciplinary synthesis
Present-day reach: Multi-domain
Rationale: Displaying distributions, percentiles, thresholds, and sensitivity is analytical visualization of stochastic results.
Related originating lineages:
- Human-Computer Interaction — Dashboard design makes uncertainty legible to decision makers.
- Operations Research — Risk thresholds translate simulation output into decisions.
- Statistics & Experimental Design — Percentiles and sensitivity summaries must represent sampling and model uncertainty correctly.
Review resolution: The blind reviewers agree that data_science is the primary origin and differ only on alternate origin disagreement, origin mode disagreement, domain reach disagreement, encyclopedia synthesis disagreement. I preserve every independently explained alternate from both records rather than imposing a numeric cap. I retain cross_disciplinary_synthesis because the combined evidence shows material contributions from several lineages. The broader reach of multi_domain records portability separately from historical provenance; encyclopedia_synthesis=true preserves the affirmative synthesis judgment where either reviewer identified one.
Encyclopedia synthesis: The exact catalogued form synthesizes established practice rather than reproducing a single standard historical label.
Review outcome: Reconciled after independent review; high confidence.
Notes¶
[n1] The McNamara fallacy is the error of trusting only what can be measured and displayed, discarding what resists quantification as unimportant. On a dashboard it manifests as a precise chart displacing the softer but decisive question of whether the underlying assumptions hold — which is why honesty markers must share the frame with the headline number. ↩