This paper studies a single-period inventory problem with random yield and demand, where the loss-averse preferences are adopted to describe the retailer’s (newsvendor’s) decision-making behavior. When the loss-averse retailer orders, the fraction of good units in a batch is stochastic. He will choose an order quantity to maximize his expected utility. Both shortage cost and no shortage cost are considered, respectively. The retailer’s optimal ordering policies are obtained, then the impacts of loss aversion, price and cost on the optimal order quantity are analysed. For the model without shortage cost, the loss-averse retailer’s optimal order quantity is always less than the risk-neutral retailer’s, and decreasing in the loss aversion level. While for the model with shortage cost, the loss-averse retailer’s optimal order quantity may be larger than the risk-neutral retailer’s, and increasing in the loss aversion level. Moreover, it may be decreasing in selling price and increasing in purchasing cost, which will never occur in the case of zero shortage cost. The numerical experiments are conducted to demonstrate our theoretical results.