Missing Not at Random
Missing not at random describes a missing-data mechanism in which the probability that a value is unobserved depends on that unobserved value even after conditioning on the available observed information.
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.
Mixed Effects Model
A mixed effects model is a regression with fixed and random effects, used in health economics for repeated or clustered data such as costs and utilities.
Mixture Cure Model
A mixture cure model is a survival model treating patients as a cured group with only background mortality and an uncured group still at risk, used in HTA.
Mixture Model
A statistical model representing a population as a combination of two or more distinct subgroups, each following its own underlying distribution.
Model Averaging
Model averaging combines results from several plausible models, weighted by their support, so health economic estimates reflect doubt about model choice.
Model Diagnostics
Model diagnostics are checks that show whether a health economic model, or a statistical model feeding it, fits its data and behaves as intended.
Model Selection
The process of choosing a model from plausible alternatives using criteria suited to the intended question, data, predictive or explanatory performance, and decision context.
Model Validation
Model validation is the testing of a health economic model against expert review, other models and observed data to judge whether it is fit for a decision.
Monetary Valuation
Monetary valuation expresses a health outcome or other non-market good in money terms, using stated preference, revealed preference or wellbeing methods.
Monte Carlo Error
Monte Carlo error is the random numerical difference between a finite-simulation estimate and the target quantity it would approach with sufficiently many valid draws under the specified model.
Monte Carlo Integration
Monte Carlo integration estimates an integral, such as a model's expected cost or QALYs, by averaging the integrand over randomly sampled inputs.
Monte Carlo Simulation
Monte Carlo simulation runs a health economic model many times on randomly sampled inputs to estimate expected costs and QALYs and their uncertainty.
Moral Hazard
Moral hazard is the change in behaviour, such as greater use of healthcare, that occurs when insurance shields people from the full cost of their choices.
Moral Hazard in Health Insurance
Moral hazard in health insurance is extra healthcare use when cover lowers the price patients pay, and any reduced effort to stay healthy once insured.
Morris Method
A global sensitivity-screening method that samples one-input-at-a-time elementary effects across multiple model-input settings to identify influential or varying inputs.
Multi-Objective Optimisation
Multi-objective optimisation finds the efficient trade-offs when a health budget decision has conflicting goals, such as total QALYs and health equity.
Multicollinearity
Multicollinearity is near or exact linear dependence among the predictors in a cost, utility or risk regression, making their separate effects imprecise.
Multinomial Logit Model
Multinomial logit model (MNL) is a random utility choice model used to estimate preference weights from DCE data, assuming IID extreme value errors.
Multiple Imputation
Multiple imputation fills missing costs or QALYs several times with plausible draws, analyses each completed dataset and pools results by Rubin's rules.
Multiple Regression
Multiple regression models one outcome, such as patient cost or QALYs, on two or more explanatory variables, adjusting each coefficient for the others.