On (p1,…,pk)-spherical distributions

Wolf-Dieter Richter
2019 Journal of Statistical Distributions and Applications  
The class of (p 1 , . . . , p k )-spherical probability laws and a method of simulating random vectors following such distributions are introduced using a new stochastic vector representation. A dynamic geometric disintegration method and a corresponding geometric measure representation are used for generalizing the classical χ 2 -, t-and F-distributions. Comparing the principles of specialization and marginalization gives rise to an alternative method of dependence modeling.
doi:10.1186/s40488-019-0097-z fatcat:cpi3oodk6zgbxgzzk5bya7uszq