Kappa Statistic
The kappa statistic (Cohen's kappa) measures chance-corrected agreement between two raters on a categorical judgement, such as reviewers screening studies.
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.
Karnofsky Performance Status
Karnofsky Performance Status is a clinician-rated 11-level score of a cancer patient's function, 100 normal and 0 dead, used to set treatment eligibility.
Katz ADL Index
Katz ADL Index is a rating of independence in six basic activities of daily living, used to define dependency in trials and care models for older people.
KCCQ
KCCQ is a 23-item heart failure questionnaire scoring symptoms, function, social limitation and quality of life 0 to 100, used as a trial and HTA outcome.
Kendall Tau
Kendall tau is a rank correlation from minus one to one, comparing how often two rankings of health states or treatments order pairs alike or reversed.
KIDSCREEN-10
KIDSCREEN-10 is a ten-item measure of health-related quality of life and wellbeing for ages 8 to 18, scored as a Rasch T-value against European norms.
Kurtosis
Kurtosis is the standardised fourth moment of a distribution, a measure of tail heaviness that flags rare extreme values such as very high patient costs.
Language Bias
Language bias is a reporting bias in which a study's language of publication depends on its results, so reviews limited to English can misstate effects.
Large Simple Trial
A large simple trial randomises thousands of patients with simple entry rules and minimal data to detect moderate effects on death or serious disability.
Last Observation Carried Forward
Last observation carried forward (LOCF) fills missing trial follow-up values with each participant's last observed value, assuming no change after dropout.
Latent Class Analysis
Latent class analysis (LCA) finds unobserved patient subgroups from patterns in categorical data, such as recorded conditions or diagnostic test results.
Latent Growth Model
A latent growth model is a structural equation model treating each patient's starting level and rate of change in repeated health scores as latent factors.
Latent Transition Analysis
Latent transition analysis (LTA) is a longitudinal latent class method that estimates how patients move between unobserved health or behaviour states.
Latent Variable
A latent variable is an unobserved quantity, such as health-related quality of life or preference class membership, estimated from observed indicators.
Law of Large Numbers
The law of large numbers says the average of independent patient costs or simulation draws settles on the true mean as more are added.
Leave-One-Out
Leave-one-out cross-validation tests a cost or risk prediction model by refitting it without each observation in turn and predicting the one left out.
Leverage Point
A leverage point is an observation, such as one patient in a cost regression, whose predictor values lie far from the rest and can pull the fitted model.
Likelihood Ratio
A likelihood ratio is how many times as likely a test result or other evidence is under one hypothesis, such as having a disease, as under another.
Linear Regression
Linear regression models a continuous outcome, such as cost or QALYs, as a weighted sum of predictors plus error, usually fitted by least squares.
Listwise Deletion
Listwise deletion, or complete-case analysis, drops any patient missing an analysis variable, so trial costs and QALYs come only from complete records.