Uncertainty is an inherent property of observations. Abstracting the real world to conceptual objects is a step of generalisation, and the measurement, taking place on abstracted objects, propagates this uncertainty, adding systematic, gross and random errors. Each spatial analysis is infected by these sources of uncertainty. Therefore it is necessary to introduce propagation of uncertainty in spatial analysis to allow an assessment of the results. The scope of this chapter is to combine the process of observation with a mathematical model of qualitative spatial relations, modelling the randomness of tire observations. A methodology is presented for probability-based decisions about spatial relations.