: In this thesis, we present an expanded account of warranty forecasting model based on an article by Kleyner and Sandborn (2005). Our aims in this thesis are; to study the use of suitable statistical methods and distributions for warranty returns and modeling the warranty time based on warranty claims data. The warranty prediction model is based on a piecewise application of Weibull and Exponential distributions, having three parameters, which are the characteristic life and shape parameter of the Weibull distribution and the time coordinate of the junction point of the two distributions. This time coordinate is the point at which the reliability ‘bathtub’ curve exhibits a transition between early life and constant hazard rate behavior. The values of the parameters are obtained from the optimum fitting of data on past warranty claims for similar products. To combine the first two sections of the bathtub curve and to provide a best fit for the warranty data they suggest using a conditional reliability equation: R(t) = R(ts)R(ts à t), t ts. Where: R(t) = reliability at the time interval t . ts = predetermined time coordinate. R(ts) = reliability at the time ts . R(ts à t) = probability of reaching the time point t , under the condition that time ts ha already been reached. Analysis of the existing data shows that ts , can be determined as the time coordinate where hazard rate stabilizes, and the failure data with decreasing failure rate in the range [0; ts] could be fitted by Weibull distribution. Similarly the failure data in the range [ts; t] could be fitted by Exponential distribution, since the failure rate would remain relatively constant in this range. It is also important to study the multi-dimensional aspect of warranty specifications. Since automotive warranties are usually expressed in both time and mileage terms, for example, warranty can expressed in terms of {T0, M0} with T0 being specified maximum time period and M0 specified maximum mileage, which is a two-dimensional warranty.