Multivariate Case
The immediate generalisation of the above, which considers only scalar random variables, is to multivariate heteroscedasticity. One version of this is to use covariance matrices as the multivariate measure of dispersion. Several authors have considered tests in this context, for both regression and grouped-data situations.
Read more about this topic: Heteroscedasticity
Famous quotes containing the word case:
“If someone does something we disapprove of, we regard him as bad if we believe we can deter him from persisting in his conduct, but we regard him as mad if we believe we cannot. In either case, the crucial issue is our control of the other: the more we lose control over him, and the more he assumes control over himself, the more, in case of conflict, we are likely to consider him mad rather than just bad.”
—Thomas Szasz (b. 1920)