Abiotic conditions, biotic factors, and disturbances can act as filters that control community structure and composition. Understanding the relative importance of these drivers would allow us to understand and predict the causes and consequences of changes in community structure. We used long-term data (1989-2002) from the sagebrush steppe in the state of Washington, USA, to ask three questions: (1) What are the key drivers of community-level metrics of community structure? (2) Do community-level metrics and functional groups differ in magnitude or direction of response to drivers of community structure? (3) What is the relative importance of drivers of community structure? The vegetation in 2002 was expressed as seven response variables: three community-level metrics (species richness, total cover, compositional change from 1989 to 2002) and the relative abundances of four functional groups. We used a multi-model inference framework to identify a set of top models for each response metric beginning from a global model that included two abiotic drivers, six disturbances, a biotic driver (initial plant community), and interactions between the disturbance and biotic drivers. We also used a permutational relative variable importance metric to rank the influence of drivers. Moisture availability was the most important driver of species richness and of native forb cover. Fire was the most important driver of shrub cover and training area usage was important for compositional change, but disturbances, including grazing, were of secondary importance for most other variables. Biotic drivers, as represented by the initial plant communities, were the most important driver for total cover and for the relative covers of exotics and native grasses. Our results indicate that the relative importance of drivers is dependent on the choice of metric, and that drivers such as disturbance and initial plant community can interact.