We extend qualitative reasoning with estimations of the relative likelihoods of the pos sible qualitative behaviors . We estimate the likelihoods by viewing the dynamics o f a system as a Markov chain over its transition graph. This corresponds to addin g probabilities to each of the transitions. The transition probabilities follow directl y from theoretical considerations in simple cases . In the remaining cases, one must derive them empirically from numeric simulations, experiments, or subjective estimates . Once the transition probabilities have been estimated, the standard theory of Marko v chains provides extensive information about asymptotic behavior, including a partition into persistent and transient states, the probabilities for ending up in each state, an d settling times . Even rough estimates of transition probabilities provide useful qualita tive information about ultimate behaviors, as the analysis of many of these quantitie s is insensitive to perturbations in the prob...