A. García Nogales, P. Pérez
Markov kernels (also called stochastic kernels, or transition probabilities) play a decisive role in probability and mathematical statistics theories, and are
a generalization of the concepts of sigma-field and random variable. An extension of conditional independence to the framework of Markov kernels is used to obtain generalized versions of two known results about conditional independence. One of them is a recently published result by the authors about the relationship between conditional and unconditional independence. The second one is a result that can be found in a book by Florens, Mouchart and Rolin, where it is considered as the main result on conditional independence (in fact, many interesting applications in the framework of Bayesian statistical theory are presented there).
Keywords: Conditional independence; Markov kernels
Scheduled
Posters I
June 7, 2022 12:00 PM
Faculty Hall