The functional properties of central synapses are difficult to study because they can be modulated either presynaptically or postsynaptically, each connection has multiple contacts and release at each contact is stochastic. Moreover, studying central synapses with electrophysiology is complicated by the fact that synapses are often remote from the recording site and signals are often difficult to resolve above the noise. This together with the fact that central synapses often have few release sites and have nonuniform quantal parameters makes classical quantal analysis methods difficult to apply. Here, we discuss an alternative approach, multiple-probability fluctuation analysis (MPFA), which can be used to estimate nonuniform quantal parameters from fits of the relationship between the variance and mean amplitude of postsynaptic responses, recorded at different release probabilities. We illustrate the experimental protocols and the analysis procedure that should be followed to perform MPFA and interpret the estimated parameters.