In order to evaluate the vulnerability states of small cities and towns correctly and then to establish scientific basis for disaster prevention and reduction

a stochastic assessment method for the vulnerability of small cities and towns by using Bayesian formula was proposed.In this method

according to the maximum likelihood ordering principle

the assessment order of each index of actual small cities and towns was firstly derived through calculating the probability of each of those vulnerability indices belonging to the assessment order used in the vulnerability assessment criteria of small cities and towns.Secondly

the integrated vulnerability assessment order of small cities and towns was derived by using the maximum weighted probability principle.Tested by examples together with the other two methods

i.e.the fuzzy assessment method and extension matter-element method

the results verify effectively that this method is useful and feasible.