Abstract
Two new families of matrix variate distributions are introduced. They are based on matrix normal distribution and yet can be used to model data involving skewness. The properties of the two families are investigated. Among others, the marginals, conditionals, stochastic representation, linear and quadratic forms are studied.
| Original language | English |
|---|---|
| Pages (from-to) | 179-194 |
| Number of pages | 16 |
| Journal | Statistics |
| Volume | 42 |
| Issue number | 2 |
| DOIs | |
| State | Published - Apr 2008 |
Keywords
- Construction of random matrix
- Linear forms
- Matrix variate distribution
- Quadratic forms
- Random matrix
- Skew-normal distribution
- Stochastic representation
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty