Generalized Gamma Model
The generalised gamma model is a three-parameter survival model used in health economics to extrapolate trial data, nesting the Weibull and log-normal.
Encyclopaedia
Explore comprehensive, evidence-informed explanations of key health economics concepts, including their development, application and relationships to other concepts. Published entries are validated through human expert review.
Concepts, entries and ontology terms
A concept page is a published entry on the wiki. Some concepts also have a full encyclopaedia article. The Health Economics Ontology (HEO) holds every concept, including dictionary terms without an article, so it is larger than the list of published pages. The knowledge graph shows how concepts relate to each other.
Genetic Algorithm
A genetic algorithm is a search method based on natural selection that evolves candidate solutions, used to calibrate and optimise health economic models.
Gibbs Sampling
Gibbs sampling is a Markov chain Monte Carlo method that fits Bayesian models, such as meta-analyses, by drawing each parameter in turn given the others.
Global Sensitivity Analysis
Global sensitivity analysis (GSA) measures how much each uncertain input of a health economic model drives variation in results as all inputs vary at once.
Gompertz Distribution
A probability distribution characterised by a hazard rate rising exponentially with time, originally developed to describe human mortality increasing with age.
Gompertz Model
A survival model based on the Gompertz distribution, assuming the hazard rate rises exponentially over time, a pattern common in age-related mortality.
Goodness of Fit
Goodness of fit describes how adequately a statistical model or probability distribution represents the observed data for its intended purpose.
Goodness of Fit Test
A goodness of fit test assesses whether a specified discrepancy between observed data and a proposed probability model is unusually large under that model’s sampling assumptions.
Gradient Descent
Gradient descent is an iterative first-order optimization method that reduces a differentiable objective function by repeatedly moving the parameter vector in the direction opposite its gradient.
Grid Search
Grid search is an optimisation method that tests every combination of preset parameter values, used to calibrate and tune health economic models.
Hazard Rate
The hazard rate is the instantaneous event rate among people still event free at a given time in survival models. Not a probability, it can exceed 1.
Health Economic Model
A health economic model, or decision model, is a mathematical framework combining evidence to estimate the costs and health outcomes of healthcare options.
Hidden Markov Model
A hidden Markov model (HMM) is a Markov model of disease progression whose true states are unobserved and inferred from error-prone tests or markers.
Importance Sampling
Importance sampling is a Monte Carlo method that samples rare or influential model inputs more often, then reweights draws so estimates match the model.
Individual Patient Simulation
Individual patient simulation is a modelling approach that generates separate patient histories under specified rules and aggregates their costs and health outcomes for a target population.
Integer Programming
Integer programming chooses which indivisible health programmes or medicines to fund to maximise health gain, such as QALYs, within a fixed budget.
Interaction Effect
An interaction effect is the part of two factors' joint effect on a health outcome or model result that adding their separate effects does not explain.
Interpolation
Interpolation estimates a value between observed or modelled data points using an assumed relationship across the interval.
Interval Censoring
Interval censoring occurs when a patient's event time, such as disease progression, is known only to lie between two assessments, such as two trial scans.
Joint Model
A joint model fits a repeatedly measured biomarker and time to an event such as death together, so survival estimates for economic models reflect the link.