Dictionary
The Dictionary provides concise definitions of health economics terms, arranged alphabetically for quick reference. Use it to understand unfamiliar terminology or confirm the meaning of a specific term.
A
- Algorithm
- A finite sequence of well-defined computational steps for solving a problem or performing a calculation.
- Algorithm Development
- The process of creating a structured, step-by-step clinical decision pathway guiding appropriate diagnosis or treatment for a specific condition.
B
- Big O Notation
- An asymptotic notation that expresses an upper bound on how an algorithm?s resource use grows as input size increases, disregarding constant factors and lower-order terms.
- Binary Search
- A search algorithm for sorted data that repeatedly compares the target with the middle item and eliminates the half in which the target cannot occur.
C
- Clinical Algorithm
- A structured, step-by-step clinical decision pathway outlining recommended diagnostic or treatment steps for a condition, increasingly built into decision support systems.
- Computational Complexity
- A measure of the computational resources required by an algorithm as the size of the input increases.
- Convergence Assessment
- An evaluation of whether an iterative algorithm, such as a Markov chain Monte Carlo simulation, has run enough iterations to produce stable results.
D
- Data Structure
- An organization of information designed to support efficient storage, access, modification, or processing by algorithms.
- Decision Algorithm
- A structured framework guiding how an assessment body should weigh and combine evidence and criteria to reach a final recommendation.
- Diagnostic Analytics
- The application of data analysis techniques to support diagnostic decision-making, from statistical risk prediction models to machine learning algorithms trained on clinical data.
- Digital Safety
- The degree to which a digital health technology avoids causing unintended harm, covering both clinical safety and data security or algorithmic bias.
- Divide and Conquer
- An algorithmic technique that divides a problem into smaller instances, solves those instances?often recursively?and combines their solutions.
- Dynamic Programming
- An algorithmic technique that solves a problem by combining solutions to overlapping subproblems and storing those solutions to avoid repeated computation.
G
- Genetic Algorithm
- An optimisation technique inspired by evolution that iteratively selects and combines the best candidate solutions across generations to improve results.
- Gibbs Sampling
- A Markov chain Monte Carlo algorithm generating samples from a complex joint distribution by iteratively sampling each variable from its conditional distribution.
- Gradient Descent
- An iterative optimisation algorithm adjusting parameters in the direction that most rapidly reduces an objective function until a minimum is reached.
H
- Health Index
- A single numerical summary of overall health status, derived by combining scores across multiple health dimensions using a specified scoring algorithm.
I
- Indirect Elicitation
- A health state valuation approach in which a descriptive questionnaire's responses are converted into a utility value using a pre-existing scoring algorithm.
- Indirect Utility Assessment
- The process of obtaining a health state utility value by applying a scoring algorithm from a prior valuation study to a respondent's questionnaire answers.
- Interior-Point Method
- An optimisation algorithm that approaches the optimum of a constrained problem by traversing the interior of the feasible region.
K
- Kalman Filter
- A recursive algorithm estimating a dynamic system's unknown state over time by combining noisy observations with a model of how the system evolves.
M
- Mapping Algorithm
- A statistical model predicting a health utility value from responses on a non-preference-based instrument, used when a preference-based measure was not collected.
- Mapping Function
- The specific statistical relationship, typically estimated through regression, used within a mapping algorithm to convert a health status score into a predicted utility value.
- Markov Chain Monte CarloMCMC
- A class of algorithms generating samples from a complex probability distribution by constructing a Markov chain that converges to that distribution.
- Metropolis-Hastings
- A Markov chain Monte Carlo algorithm generating samples by proposing candidate values and accepting or rejecting them by a rule ensuring convergence.
N
- Nelder-Mead Method
- A numerical optimisation algorithm searching for a function's minimum using a moving shape, called a simplex, without needing the function's derivative.
P
- Pseudo-Random Number
- A number generated by a deterministic algorithm that approximates the statistical properties of true randomness, used because genuine randomness is hard to compute.
R
- Recursive Algorithm
- An algorithm that solves a problem by invoking itself on one or more smaller or simpler instances until a base condition is reached.
S
- Scoring Algorithm
- The specific formula, derived from a population valuation study, used to convert health status questionnaire responses into a single utility value.
- Sequential Monte Carlo
- A class of algorithms, including particle filtering, estimating a sequence of unknown quantities over time by updating weighted samples as new data arrive.
- SF-6DShort Form-6 Dimension
- A preference-based utility measure derived from a subset of SF-36 or SF-12 items, combined using a scoring algorithm into a single utility index.
- Simplex Method
- An optimisation algorithm that solves linear programming problems by moving systematically between feasible solutions until the optimum is found.
- Sorting Algorithm
- An algorithm that arranges a collection of items into a predetermined order according to their keys or a comparison rule.
- Space Complexity
- A measure of how the memory requirements of an algorithm grow as the size of the input increases.
T
- Time Complexity
- A measure of how the execution time of an algorithm grows as the size of the input increases.
- Treatment Algorithm
- A structured, step-by-step clinical decision pathway outlining the recommended sequence of treatment decisions for a specific condition.
V
- Value Set Development
- The process of designing, conducting, and analysing a population valuation study to produce a scoring algorithm for a health status instrument.