Abstract
Mahalanobis-type distances in which the shape matrix is derived from a consistent high-breakdown robust multivariate location and scale estimator can be used to find outlying points. Hardin and Rocke (http://www.cipic.ucdavis.edu/~dmrocke/preprints.html) developed a new method for identifying outliers in a one-cluster setting using an F distribution. We extend the method to the multiple cluster case which gives a robust clustering method in conjunction with an outlier identification method. We provide results of the F distribution method for multiple clusters which have different sizes and shapes.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 625-638 |
| Number of pages | 14 |
| Journal | Computational Statistics and Data Analysis |
| Volume | 44 |
| Issue number | 4 |
| DOIs | |
| State | Published - Jan 28 2004 |
Fingerprint
Keywords
- Minimum covariance determinant
- Outlier detection
- Robust clustering
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Statistics, Probability and Uncertainty
- Electrical and Electronic Engineering
- Computational Mathematics
- Numerical Analysis
- Statistics and Probability
Cite this
Outlier detection in the multiple cluster setting using the minimum covariance determinant estimator. / Hardin, Johanna; Rocke, David M.
In: Computational Statistics and Data Analysis, Vol. 44, No. 4, 28.01.2004, p. 625-638.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Outlier detection in the multiple cluster setting using the minimum covariance determinant estimator
AU - Hardin, Johanna
AU - Rocke, David M
PY - 2004/1/28
Y1 - 2004/1/28
N2 - Mahalanobis-type distances in which the shape matrix is derived from a consistent high-breakdown robust multivariate location and scale estimator can be used to find outlying points. Hardin and Rocke (http://www.cipic.ucdavis.edu/~dmrocke/preprints.html) developed a new method for identifying outliers in a one-cluster setting using an F distribution. We extend the method to the multiple cluster case which gives a robust clustering method in conjunction with an outlier identification method. We provide results of the F distribution method for multiple clusters which have different sizes and shapes.
AB - Mahalanobis-type distances in which the shape matrix is derived from a consistent high-breakdown robust multivariate location and scale estimator can be used to find outlying points. Hardin and Rocke (http://www.cipic.ucdavis.edu/~dmrocke/preprints.html) developed a new method for identifying outliers in a one-cluster setting using an F distribution. We extend the method to the multiple cluster case which gives a robust clustering method in conjunction with an outlier identification method. We provide results of the F distribution method for multiple clusters which have different sizes and shapes.
KW - Minimum covariance determinant
KW - Outlier detection
KW - Robust clustering
UR - http://www.scopus.com/inward/record.url?scp=0344513198&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0344513198&partnerID=8YFLogxK
U2 - 10.1016/S0167-9473(02)00280-3
DO - 10.1016/S0167-9473(02)00280-3
M3 - Article
AN - SCOPUS:0344513198
VL - 44
SP - 625
EP - 638
JO - Computational Statistics and Data Analysis
JF - Computational Statistics and Data Analysis
SN - 0167-9473
IS - 4
ER -