Most warranty studies assume that the usage intensity is the same for all buyers. However, in real life the usage intensity varies across the population of buyers. In the general case, one can divide the population into categories. This has implications for manufacturers of products. Should a manufacturer produce one product and offer different warranties for the groups or produce different products (one for each group) and offer the same warranty. A warranty cost analysis is needed to choose between these options. The analysis complicated by factors such as adverse selection , buyers attitude to risk and the price structure. In this paper we develop models to study the expected warranty cost for products with free replacement warranty with varying usage intensity. Numerical examples are presented.