Search

The Markovian arrival process (MAP) has proven a versatile model for fitting dependent and non-exponential interarrival times, with a number of applications to queueing, teletraffic, reliability or finance. Despite theoretical properties of MAPs and models involving MAPs are well studied, their estimation remains less explored. This paper examines maximum likelihood estimation of the second-order MAP using a recently obtained parameterization of the two-state MAPs., Comment: 20 PAGES, 2 FIGURES

The capability of modeling non-exponentially distributed and dependent inter-arrival times as well as correlated batches makes the Batch Markovian Arrival Processes (BMAP) suitable in different real-life settings as teletraffic, queueing theory or actuarial contexts. An issue to be taken into account for estimation purposes is the identifiability of the process. This is an open problem concerning BMAP-related processes. This paper explores the identifiability issue of the two-state BMAP noted BMAP2(k), where k is the maximum batch arrival size. It is proven that for k = 2 the process cannot be identified, under the assumptions that both the interarrival times and batches sizes are observed. Additionally, a method to obtain an equivalent BMAP2(2) to a given one is provided.

In this work, we discuss Bayesian estimation of multinomial probabilities associated with a finite alphabet A under incomplete experimental information. Two types of prior information are considered: (i) number of letters needed to see a particular pattern for the first time, and (ii) the fact that for two fixed words one appeared before the other.

In this work, we discuss Bayesian estimation of multinomial probabilities associated with a finite alphabet A under incomplete experimental information. Two types of prior information are considered: (i) number of letters needed to see a particular pattern for the first time, and (ii) the fact that for two fixed words one appeared before the other.