CANONICAL VARIATE ANALYSIS-A GENERAL MODEL FORMULATION (Q3223670)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3890495
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | CANONICAL VARIATE ANALYSIS-A GENERAL MODEL FORMULATION |
scientific article; zbMATH DE number 3890495 |
Statements
CANONICAL VARIATE ANALYSIS-A GENERAL MODEL FORMULATION (English)
0 references
1984
0 references
elliptical densities
0 references
comparison of solutions
0 references
general canonical variate model
0 references
maximum likelihood estimators
0 references
robust estimation
0 references
estimation of missing values
0 references
adequacy of hypothetical vectors
0 references
comparison of several sets of data
0 references
0.81190425157547
0 references
0.8105029463768005
0 references
0.7963482737541199
0 references
0.7962254285812378
0 references
0.7962254285812378
0 references
The original canonical variate analysis was a distribution-free procedure. It makes no explicit distinction between the population and the sample. In this paper, a general canonical variate model is considered. Parameters are introduced for the canonical vectors, group coordinates and covariance matrix, and maximum likelihood estimators are derived. The method makes a distinction between the population and the sample, a distinction not always made in this area. The model provides a natural basis for the evaluation of various hypotheses. Having introduced the general canonical variate model, a number of practical aspects are discussed, including robust estimation, estimation of missing values, the adequacy of hypothetical vectors, and comparison of several sets of data. An advantage of this general canonical variate model is that models appropriate for the problem can be set up. Another advantage is the possibility to compare canonical variate solutions for several sets of data.
0 references