|
|
|
| Definition: |
The term occurs in statistical work in at least three contexts:
(a) In the theory of order relations, the rank of a single observation among a set is its ordinal number when the set is ordered according to some criterion such as values of a variate borne by the individuals.
(b) In matrix theory the term occurs in its usual mathematical sense, being the greatest number r of linearly independent rows or columns which can be found in it.
(c) Derived from the previous usage, the rank of multivariate distribution is the rank of its dispersion matrix, and is thus the number of variates which are independent in the sense of not being connected by linear equations.
|
| Source
Publication: |
|
A Dictionary of Statistical Terms, 5th edition, prepared for the International Statistical Institute by F.H.C. Marriott. Published for the International Statistical Institute by Longman Scientific and Technical.
|
| Statistical
Theme: Methodological information (metadata) |
| Created
on Sunday, May 26, 2002 |
| Last
updated on Wednesday, March 12, 2003 |
|
|
|
|
|
|
|
|
|
|
|
|
|
