AbstractThis paper presents a stochastic inventory model for situations in which, during a stockout period, a fractionβof the demand is backordered and the remaining fraction 1–βis lost. The model is suggested by the customers' different reactions to a stockout condition: during the stockout period, some patient customers wait until their demand is satisfied, while other impatient or urgent customers cannot wait and have to fill their demand from another source. The cost of a backorder is assumed to be proportional to the length of time for which the backorder exists, and a fixed penalty cost is incurred per unit of lost demand. Based on a heuristic treatment of a lot-size reorder-point policy, a mathematical model representing the average annual cost of operating the inventory system is developed. The optimal operating policy variables minimizing the average annual cost can be calculated iteratively. At the extremesβ= 1 andβ= 0, the model presented reduces to the usual backorders and lost sales case, respectively.