Barankin bound

E621102

The Barankin bound is a fundamental lower bound in statistical estimation theory that generalizes and can be tighter than the Cramér–Rao bound for the variance of unbiased estimators, especially in non-regular or finite-sample settings.

Try in SPARQL Jump to: Statements Referenced by

Statements (41)

Predicate Object
instanceOf lower bound in estimation theory
statistical bound
appliesTo unbiased estimators
canBe tighter than Cramér–Rao bound
canHandle bounded parameter spaces
discrete parameter spaces
non-differentiable likelihood functions
characterizes minimum achievable variance of unbiased estimators
comparedTo Bhattacharyya bound NERFINISHED
Cramér–Rao bound NERFINISHED
Hammersley–Chapman–Robbins bound NERFINISHED
dependsOn family of probability distributions
parameter point of interest
set of alternative parameter values
doesNotRequire regularity conditions of Cramér–Rao bound
field mathematical statistics
statistical estimation theory
generalizes Cramér–Rao bound NERFINISHED
goal characterize fundamental limits of estimation accuracy
hasFormulation optimization over finite sets of parameter points
hasProperty can be approximated numerically
can be difficult to compute exactly
introducedIn 20th century
namedAfter Eugene Barankin NERFINISHED
provides lower bound on covariance matrix of unbiased estimators
performance benchmark for estimators
relatedTo Fisher information NERFINISHED
information inequality
minimum variance unbiased estimation
typeOf local lower bound
usedAs benchmark for estimator design
tool for performance analysis in engineering systems
usedIn array processing
communications theory
direction-of-arrival estimation
finite-sample settings
non-regular estimation problems
parametric estimation
signal processing
validFor finite samples
non-asymptotic analysis

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Cramér–Rao bound relatedConcept Barankin bound