Service parts management is an integral component of customer satisfaction. The service parts supply chain has a number of unique challenges that differentiate it from retail and manufacturing supply chains. These challenges include: unpredictable and lumpy demand, limited storage capacity, high demand service rate requirements, and high risk of obsolescence. This research focuses on the use of substitution as a policy tool to aid in service part supply chain management; particularly with respect to low inventory and high dollar value components. In one part of this dissertation, a Markov chain is used to model unidirectional substitution with dissimilar part reliability. In addition, this work investigates probabilistic substitution policies that allow substitution to be employed on a partial basis. This research also utilizes a Poisson process to explore steady state optimization with probabilistic substitution for a model in which a non-primary part is utilized solely as a substitute for primary parts. The models demonstrate that both substitution protocols can significantly enhance customer performance benchmarks. Unidirectional substitution policies improve fill rate and backorder levels for the machine upon which substitution is performed. The price of this improvement is the cost of additional ordering and inventory, along with decreased fill rate and backorder performance, on the machine whose parts are used for substitution. Substitution, using a part solely carried for that purpose, increases performance levels without higher inventory levels of either primary part. However, this type of substitution requires the inclusion of an additional inventory part and the associated costs.