
Given a discrete-valued sample we wish to decide whether it was generated by a distribution belonging to a family , or it was generated by a distribution belonging to a family . In this work we assume that all distributions are stationary ergodic, and do not make any further assumptions (e.g. no independence or mixing rate assumptions). We would like to have a test whose probability of error (both Type I and Type II) is uniformly bounded. More precisely, we require that for each there exist a sample size such that probability of error is upper-bounded by for samples longer than . We find some necessary and some sufficient conditions on and under which a consistent test (with this notion of consistency) exists. These conditions are topological, with respect to the topology of distributional distance.
View on arXiv