Relational clustering has received much attention from researchers in the last decade. In this paper we present a parametric method that employs a combination of both hard and soft clustering. Based on the corresponding Markov chain of an affinity matrix, we simulate a probability distribution on the states by defining a conditional probability for each subpopulation of states. This probabilistic model would enable us to use expectation maximization for parameter estimation. The effectiveness of the proposed approach is demonstrated on several real datasets against spectral clustering methods.