Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Simulation›Deterministic Sensitivity Analysis — Systematic Parameter Variation for Model Robustness
Process / pipelineSimulation / optimization

Deterministic Sensitivity Analysis — Systematic Parameter Variation for Model Robustness

Also known as: DSA, One-Way Sensitivity Analysis, Tornado Diagram Analysis, Parametric Sensitivity Analysis

Deterministic Sensitivity Analysis (DSA) tests how model outputs change when individual or combined input parameters are varied across plausible ranges, one at a time or in structured combinations, without invoking probabilistic sampling. It is the standard approach in economic modeling, decision trees, and mathematical programming to identify which parameters drive conclusions and to demonstrate model robustness to regulators, reviewers, and stakeholders.

ScholarGate
  1. Process / pipeline
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Deterministic Sensitivity Analysis
MONTE-CARLO-SIMULATIONStochastic Sensitivity A…Deterministic Scenario A…

When to use it

Use DSA when you need a transparent, auditable account of model uncertainty for regulators, health technology assessment bodies, or peer review — contexts where probabilistic sampling would be opaque or computationally expensive. It is appropriate when parameter ranges are known but distributional forms are not, or when the model run time makes Monte Carlo infeasible. Use one-way DSA for initial screening of influential parameters, then two-way or threshold analysis for parameters that approach a decision-changing value. Do NOT use DSA as a substitute for probabilistic analysis when joint parameter uncertainty is substantial and correlated — it can understate combined uncertainty. Avoid it when the model is highly nonlinear, as one-at-a-time variation may miss interaction effects that only appear when multiple parameters shift together.

Strengths & limitations

Strengths
  • Fully transparent and reproducible: every result can be traced to an explicit parameter setting with no sampling variance.
  • Computationally cheap: requires only as many model runs as the number of parameters times the number of test values, making it feasible for large or slow models.
  • Communicates uncertainty intuitively via tornado diagrams that non-technical audiences and decision-makers can readily interpret.
  • Identifies threshold values — the exact input level at which a decision flips — providing actionable guidance for data collection priorities.
  • Required or strongly recommended by health technology assessment guidelines (NICE, CADTH, EMA) and economic evaluation reporting standards.
  • Works with any model type — decision trees, Markov models, linear programs, spreadsheet models — without requiring distributional assumptions.
Limitations
  • One-at-a-time variation ignores parameter interactions and correlations, potentially missing combinatorial effects that occur in practice.
  • Does not produce a probability distribution over outcomes, so it cannot quantify the likelihood that a conclusion is correct.
  • The choice of parameter ranges is subjective and can be manipulated to reach desired conclusions if not grounded in prespecified evidence.
  • Scales poorly for models with very large numbers of parameters — the number of required runs grows linearly, but visual representation becomes difficult beyond 20–30 parameters.
  • Extreme-scenario (worst/best case) results may be implausibly pessimistic or optimistic if all parameters are simultaneously at their extremes.

Frequently asked

What is the difference between one-way and two-way deterministic sensitivity analysis?

One-way DSA varies a single parameter at a time while holding all others at baseline, isolating each parameter's individual influence. Two-way DSA varies two parameters simultaneously across a grid of combinations, producing a contour or table of outcomes that reveals interaction effects between the two parameters. One-way is used for initial screening; two-way for pairs that both approach a decision threshold.

When should I use DSA instead of probabilistic sensitivity analysis (PSA)?

Use DSA when distributional forms for parameters are unknown, when the model is computationally expensive, when regulatory guidelines require it for transparency, or as a first step to identify which parameters warrant distributional specification for PSA. For decision-making under substantial joint uncertainty, PSA is preferred because it captures the full probability distribution of outcomes. DSA and PSA are complementary, not competing — best practice uses both.

How do I choose the range for each parameter in DSA?

Ranges should be prespecified before analysis and grounded in evidence: literature confidence intervals, clinical expert elicitation, regulatory guidance documents, or the observed range in available data sources. Ranges should not be chosen to support a preferred conclusion. For health economic models, 95% confidence intervals from the primary study are standard; for other domains, documented minimum and maximum observed values are common.

What is a tornado diagram and how do I read it?

A tornado diagram is a horizontal bar chart where each bar represents one parameter. The bar extends left (low-value outcome) and right (high-value outcome) from the baseline output. Bars are sorted from widest (most influential) at the top to narrowest (least influential) at the bottom, creating the tornado shape. A vertical line marks the baseline. Bars that cross the decision threshold line indicate parameters that can individually reverse the conclusion.

Does DSA apply only to health economics, or is it used more broadly?

DSA is used across any field relying on quantitative models with uncertain inputs: engineering, environmental science, finance, operations research, and climate modeling all employ deterministic sensitivity analysis routinely. The tornado diagram format and one-at-a-time approach are domain-agnostic; health economics has simply codified reporting requirements most explicitly.

Sources

  1. Saltelli, A., Tarantola, S., Campolongo, F., & Ratto, M. (2004). Sensitivity Analysis in Practice: A Guide to Assessing Scientific Models. John Wiley & Sons, Chichester. ISBN: 9780470870938
  2. Briggs, A., Sculpher, M., & Buxton, M. (1994). Uncertainty in the economic evaluation of health care technologies: the role of sensitivity analysis. Health Economics, 3(2), 95–104. DOI: 10.1002/hec.4730030206 ↗

How to cite this page

ScholarGate. (2026, June 3). Deterministic Sensitivity Analysis — Systematic Parameter Variation for Model Robustness. ScholarGate. https://scholargate.app/en/simulation/deterministic-sensitivity-analysis

Related methods

MONTE-CARLO-SIMULATIONStochastic Sensitivity Analysis

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • MONTE-CARLO-SIMULATIONDecision-making↔ compare
  • Stochastic Sensitivity AnalysisSimulation↔ compare
Compare side by side →

Referenced by

Deterministic Scenario Analysis

Similar methods

Stochastic Sensitivity AnalysisDeterministic Scenario AnalysisRobust Sensitivity AnalysisPolicy Scenario Sensitivity AnalysisDeterministic Markov ModelMulti-objective sensitivity analysisPolicy Scenario Monte Carlo SimulationBayesian Sensitivity Analysis

Related reference concepts

Sensitivity Analysis in Economic EvaluationCost-Effectiveness AnalysisCost-Effectiveness AnalysisEconomic Modeling and SimulationHealth Economics Methods and Quantitative AnalysisEconomic Evaluation Methods

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Deterministic Sensitivity Analysis (Deterministic Sensitivity Analysis — Systematic Parameter Variation for Model Robustness). Retrieved 2026-07-21 from https://scholargate.app/en/simulation/deterministic-sensitivity-analysis · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Saltelli, A. et al.; widely formalized across operations research and health economics
Year
1950s–1970s (formalized)
Type
Parameter variation / robustness testing
DataType
Quantitative model outputs and input parameter ranges
Subfamily
Simulation / optimization
Related methods
MONTE-CARLO-SIMULATIONStochastic Sensitivity Analysis
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account