Quadratic minimisation problems in statistics
We consider the problem subject to where is positive definite or positive semi-definite. Variants of this problem are discussed within the framework of a general unifying methodology. These include non-trivial considerations that arise when (i) and/or are not of full rank and (ii) takes special forms (especially which, under further conditions, reduces to the well-known two-sided eigenvalue solution). Special emphasis is placed on insights provided by geometrical interpretations.
Year of publication: |
2011
|
---|---|
Authors: | Albers, C.J. ; Critchley, F. ; Gower, J.C. |
Published in: |
Journal of Multivariate Analysis. - Elsevier, ISSN 0047-259X. - Vol. 102.2011, 3, p. 698-713
|
Publisher: |
Elsevier |
Keywords: | Canonical analysis Constraints Geometry Minimisation Quadratic forms Ratios Reduced rank |
Saved in:
Saved in favorites
Similar items by person
-
Applications of quadratic minimisation problems in statistics
Albers, C.J., (2011)
-
Gower, J.C., (1973)
-
RelaxMCD: Smooth optimisation for the Minimum Covariance Determinant estimator
Schyns, M., (2010)
- More ...