Cookies

We use cookies to ensure that we give you the best experience on our website. You can change your cookie settings at any time. Otherwise, we'll assume you're OK to continue.

Department of Mathematical Sciences

Seminar Archives

On this page you can find information about seminars in this and previous academic years, where available on the database.

Statistics Seminars: "Identifying similar birth-death processes using chain sequences. "

Presented by "Erik van Doorn, Department of Mathematical Sciences, University of Twente, The Netherlands ",

21 August 2000 00:00 in CM221

"The model we consider is that of a birth-death process X = {X(t)} taking values in N = {0,1,...}. To envisage such a process it is convenient to think of a particle travelling through the state space N in such a way that it stays in each state during an exponentially distributed amount of time (with state-dependent mean), after which it jumps to one of the neighbouring states with certain (state-dependent) probabilities. The stochastic variable X(t) can then be interpreted as the state of the particle at time t. We allow the probability of a downward jump in tate 0 to be positive, so that escape from N is possible. Two birth-death processes are called similar if the ratio of their transition probabilities is independent of time. We will show which condition the parameters of a birth-death process should satisfy in order that the process belongs to a (one-parameter) family of similar processes, and we will identify the members of such a family. An important ingredient in solving these problems is the use of chain sequences. The talk is based on joint work with R.B. Lenin, P.R. Parthasarathy and W.R.W. Scheinhardt. "

Contact sunil.chhita@durham.ac.uk for more information