Monte Carlo simulation repeatedly samples from specified input distributions to propagate uncertainty through a model. Its validity depends on the model structure, input distributions, dependencies and number of simulations.
Read the full entry →Research Wiki · Methods Lab
Simulation, optimisation and synthetic modelling
Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints.
Methods family
Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints.
Use methods only after defining the estimand, data structure, assumptions, validation plan and decision consequence.
Microsimulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Read the full entry →Agent-based modelling simulates individual agents with rules and interactions to study emergent system behaviour. It is useful for scenarios and mechanisms, but calibration and validation are demanding.
Read the full entry →System-dynamics modelling is a method within simulation, optimisation and synthetic modelling. Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Read the full entry →Discrete-event simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Read the full entry →Scenario simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Read the full entry →Market simulators is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Read the full entry →Conjoint simulators is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Read the full entry →Consumer-choice simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Customer-flow simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Diffusion simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Bootstrapping is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Resampling is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Jackknife estimation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Synthetic control constructs a weighted combination of comparison units that approximates the treated unit before an intervention. Post-intervention divergence is interpreted against placebo and robustness checks.
Synthetic populations is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Synthetic respondent generation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Synthetic data are artificially generated records designed to reproduce selected statistical properties or behaviours of a source population or model. Their usefulness depends on fidelity, privacy, bias, validation and whether the intended decision can tolerate model-generated evidence.
Generative adversarial networks is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Variational autoencoders is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Synthetic data are artificially generated records designed to reproduce selected statistical properties or behaviours of a source population or model. Their usefulness depends on fidelity, privacy, bias, validation and whether the intended decision can tolerate model-generated evidence.
Differential privacy is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Simulation-based power analysis is a method within simulation, optimisation and synthetic modelling. Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Sensitivity analysis is a method within simulation, optimisation and synthetic modelling. Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Stress testing is a method within simulation, optimisation and synthetic modelling. Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Robust optimisation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Browse linked method entries
Monte Carlo simulation
Monte Carlo simulation repeatedly samples from specified input distributions to propagate uncertainty through a model. Its validity depends on the model structure, input distributions, dependencies and number of simulations.
Open methodMicrosimulation
Microsimulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodAgent-based modelling
Agent-based modelling simulates individual agents with rules and interactions to study emergent system behaviour. It is useful for scenarios and mechanisms, but calibration and validation are demanding.
Open methodSystem-dynamics modelling
System-dynamics modelling is a method within simulation, optimisation and synthetic modelling. Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodDiscrete-event simulation
Discrete-event simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodScenario simulation
Scenario simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodMarket simulators
Market simulators is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodConjoint simulators
Conjoint simulators is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodConsumer-choice simulation
Consumer-choice simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodCustomer-flow simulation
Customer-flow simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodDiffusion simulation
Diffusion simulation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodBootstrapping
Bootstrapping is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodResampling
Resampling is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodJackknife estimation
Jackknife estimation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodSynthetic control
Synthetic control constructs a weighted combination of comparison units that approximates the treated unit before an intervention. Post-intervention divergence is interpreted against placebo and robustness checks.
Open methodSynthetic populations
Synthetic populations is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodSynthetic respondent generation
Synthetic respondent generation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodCopula-based synthetic data
Synthetic data are artificially generated records designed to reproduce selected statistical properties or behaviours of a source population or model. Their usefulness depends on fidelity, privacy, bias, validation and whether the intended decision can tolerate model-generated evidence.
Open methodGenerative adversarial networks
Generative adversarial networks is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodVariational autoencoders
Variational autoencoders is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodPrivacy-preserving synthetic data
Synthetic data are artificially generated records designed to reproduce selected statistical properties or behaviours of a source population or model. Their usefulness depends on fidelity, privacy, bias, validation and whether the intended decision can tolerate model-generated evidence.
Open methodDifferential privacy
Differential privacy is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodSimulation-based power analysis
Simulation-based power analysis is a method within simulation, optimisation and synthetic modelling. Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodSensitivity analysis
Sensitivity analysis is a method within simulation, optimisation and synthetic modelling. Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodStress testing
Stress testing is a method within simulation, optimisation and synthetic modelling. Computational methods for stress-testing scenarios, generating synthetic populations and choosing actions under constraints. Its usefulness depends on data structure, assumptions, validation and whether the output answers the intended decision.
Open methodRobust optimisation
Robust optimisation is a statistical or analytical concept within simulation, optimisation and synthetic modelling. It should be selected for the data-generating process and decision question rather than because software makes it available.
Open methodNo entries match this search.