Tukey's biweight
E371259
M-estimator
redescending M-estimator
robust location estimator
robust regression estimator
robust statistical estimator
Tukey's biweight is a robust statistical estimator that downweights outliers to provide resistant measures of central tendency or regression fits.
All labels observed (2)
| Label | Occurrences |
|---|---|
| Tukey's bisquare | 1 |
| Tukey's biweight canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T3600024 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tukey's biweight Context triple: [John W. Tukey, developedConcept, Tukey's biweight]
-
A.
Hotelling’s T-squared distribution
Hotelling’s T-squared distribution is a multivariate generalization of Student’s t-distribution used primarily for hypothesis testing and constructing confidence regions for mean vectors in multivariate statistics.
-
B.
Cauchy distribution
The Cauchy distribution is a continuous probability distribution with heavy tails and undefined mean and variance, often used as a classic example of pathological behavior in probability theory and statistics.
-
C.
Bhattacharyya distance
Bhattacharyya distance is a statistical measure of similarity between two probability distributions, often used in pattern recognition and classification to quantify their overlap.
-
D.
Mauchly
Mauchly is the surname of John W. Mauchly, the American physicist and co-inventor of the ENIAC, one of the earliest general-purpose electronic digital computers.
-
E.
Procrustes
Procrustes is a figure from Greek mythology known as a cruel bandit who mutilated travelers to force them to fit his iron bed, until he was slain by the hero Theseus.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tukey's biweight Target entity description: Tukey's biweight is a robust statistical estimator that downweights outliers to provide resistant measures of central tendency or regression fits.
-
A.
Hotelling’s T-squared distribution
Hotelling’s T-squared distribution is a multivariate generalization of Student’s t-distribution used primarily for hypothesis testing and constructing confidence regions for mean vectors in multivariate statistics.
-
B.
Cauchy distribution
The Cauchy distribution is a continuous probability distribution with heavy tails and undefined mean and variance, often used as a classic example of pathological behavior in probability theory and statistics.
-
C.
Bhattacharyya distance
Bhattacharyya distance is a statistical measure of similarity between two probability distributions, often used in pattern recognition and classification to quantify their overlap.
-
D.
Mauchly
Mauchly is the surname of John W. Mauchly, the American physicist and co-inventor of the ENIAC, one of the earliest general-purpose electronic digital computers.
-
E.
Procrustes
Procrustes is a figure from Greek mythology known as a cruel bandit who mutilated travelers to force them to fit his iron bed, until he was slain by the hero Theseus.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
M-estimator
ⓘ
redescending M-estimator ⓘ robust location estimator ⓘ robust regression estimator ⓘ robust statistical estimator ⓘ |
| advantage |
provides more stable estimates under contamination
ⓘ
reduces influence of extreme outliers ⓘ |
| alsoKnownAs |
Tukey's biweight
ⓘ
surface form:
Tukey's bisquare
bisquare estimator ⓘ biweight estimator ⓘ |
| appliedIn |
outlier-resistant curve fitting
ⓘ
robust estimation of mean-like quantities ⓘ robust generalized linear models ⓘ robust image analysis ⓘ robust linear regression ⓘ robust signal processing ⓘ robust time series modeling ⓘ |
| belongsTo |
robust statistics
ⓘ
statistical estimation theory ⓘ |
| comparedTo |
Huber M-estimator
ⓘ
least squares estimator ⓘ median-based estimators ⓘ |
| downweights |
observations with large residuals
ⓘ
outliers in predictor space when used with appropriate algorithms ⓘ outliers in the response variable ⓘ |
| hasProperty |
bounded influence function
ⓘ
continuous weight function ⓘ differentiable loss function ⓘ high breakdown robustness compared to least squares ⓘ less efficient than least squares under normality ⓘ nonconvex loss function ⓘ redescending influence function ⓘ |
| hasTuningParameter | c ⓘ |
| implementedIn |
MATLAB robust fitting functions
ⓘ
Python robust statistics libraries ⓘ R robust regression packages ⓘ |
| influencedBy | M-estimation theory ⓘ |
| limitation |
nonconvexity can cause multiple local minima in optimization
ⓘ
requires choice of tuning constant c ⓘ |
| namedAfter | John W. Tukey ⓘ |
| objectiveFunctionType |
loss function that flattens for large residuals
ⓘ
loss function that is quadratic near zero residuals ⓘ |
| tuningParameterControls |
degree of downweighting of large residuals
ⓘ
trade-off between robustness and efficiency ⓘ |
| usedFor |
downweighting outliers
ⓘ
resistant statistical modeling ⓘ robust estimation of central tendency ⓘ robust regression ⓘ |
| weightFunctionZeroBeyond | residuals with absolute standardized value greater than c ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Tukey's biweight Description of subject: Tukey's biweight is a robust statistical estimator that downweights outliers to provide resistant measures of central tendency or regression fits.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
Tukey's bisquare