I study the quantum mechanics of a spin interacting with an ''apparatus.'' Although the evolution of the whole system is unitary, the spin evolution is not. The system is chosen so that the spin exhibits loss of quantum coherence, or ''wave function collapse,'' of the sort usually associated with a quantum measurement. The system is analyzed from the point of view of the spin density matrix (or ''Schmidt paths''), and also using the consistent histories approach. These two points of view are contrasted with each other. Connections between the results and the form of the Hamiltonian discussed in detail.