In this paper, we present an analytical study targeted at statistically capturing the loss behavior of a RED queue. We utilize a finite-state Markov chain model. Starting from recursive equations of the model, we derive equivalent closed-form equations. We numerically validate the matching of recursive and closed-form equations. Further, we apply our model to monitor the average RED queue size in a number of sample topologies illustrating their practicality. Based on our results, we argue that our model can adapt to the changing network conditions.