Standardised Mean Difference
The standardised mean difference (SMD) is a mean difference divided by a standard deviation, used to pool continuous outcomes measured on different scales.
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.
Standardised Residual
A standardised residual is a regression residual divided by its estimated standard deviation, used to flag outlying patients in cost and outcome models.
Statistical Power
Statistical power is the probability a trial gives a significant result when a true effect of set size exists, used to size clinical and economic trials.
Statistical Significance
Statistical significance is a threshold-based conclusion that an observed result is sufficiently incompatible with a prespecified null hypothesis under a stated statistical model to meet the chosen significance level.
Structural Equation Model
A structural equation model (SEM) is a set of linked regression equations, often with latent variables, that tests hypothesised paths to health outcomes.
Structural Validity (Measurement Instrument)
Structural validity of a measurement instrument is how far a health questionnaire's scores reflect the dimensions of the construct it is meant to measure.
SUCRA
SUCRA, the surface under the cumulative ranking curve, is a 0 to 1 score of how highly a treatment ranks across all ranks in a network meta-analysis.
Summary ROC Curve
A summary ROC (SROC) curve pools diagnostic accuracy studies to show how a test's sensitivity trades off against specificity across positivity thresholds.
Surrogate Endpoint
A surrogate endpoint is a biomarker or intermediate outcome used in trials and HTA to stand in for and predict a patient-relevant outcome such as survival.
Survival Regression
Survival regression estimates how treatment and patient characteristics change the hazard of, or time to, death or progression in censored data for HTA.
SWEMWBS
SWEMWBS, the Short Warwick-Edinburgh Mental Wellbeing Scale, is a seven-item, Rasch-scored measure of positive mental wellbeing for programme evaluations.
Synthetic Control
Synthetic control estimates a health policy's effect on one region or provider using a weighted blend of untreated units that tracked it before the policy.
Systematic Review
A systematic review finds, appraises and summarises all studies on a defined question using preset, reproducible methods, as evidence for HTA and models.
T-Distribution
The t-distribution is a heavy-tailed, symmetric curve used for intervals and tests on mean costs or effects when variance is estimated from a small sample.
Tau-Squared
Tau-squared is the between-study variance in a random-effects meta-analysis, measuring how much true treatment effects differ across pooled trials.
Taylor Series Expansion
A Taylor series expansion approximates a function near a point by a polynomial built from its derivatives, used in health economics for the delta method.
Test-Retest Reliability
Test-retest reliability is the extent to which a health questionnaire, such as the EQ-5D, gives the same scores in people whose health has not changed.
Time-Lag Bias
Time-lag bias is distortion of the evidence available at a given time because studies with favourable or significant results are published sooner.
Timed Up and Go Test
Timed Up and Go Test (TUG) is a performance outcome timing how long a person takes to rise, walk 3 metres, turn and sit, used for mobility and falls risk.
Tolerance Interval
A tolerance interval is a range that, with stated confidence, encloses at least a set share of individual values in a population, such as patient costs.