An analytical approach to estimate the expected duration and variance for iterative product development projects

The paper presents an analytical method for finding the expected duration and variance of a product development (PD) project network. A PD project network is a stochastic activity network (such as a PERT network) which allows for probabilistic repetition of activities (i.e., activity rework). When rework is allowed, estimating the process duration and variance becomes difficult. Most existing literature refers to the use of simulation in such scenarios; however, few analytical methods exist to solve this problem. One such method is called the reward Markov chain (RMC) which only considers sequential activity networks and which we use as a starting point in our proposed method. In this paper, we extend the RMC method to solve mixed networks (i.e., a combination of parallel and sequential activities) and more complicated practical issues that may arise in PD environments, specifically coupled activities and parallel rework.