Habitat fragmentation can alter species distributions and lead to reduced diversity at multiple scales. Yet, the literature describing fragmentation effects on biodiversity patterns is contradictory and inconclusive, possibly because most studies fail to integrate spatial scale into experimental designs and statistical analyses. As a result, it is difficult to extrapolate the effects of fragmentation to large-scaled systems in which conservation management is of immediate importance. Objectives To explore the influence of fragmentation on biodiversity across scales, we (1) estimated the effects of habitat area, connectivity, and quality at both local (i.e. community) and regional (i.e. metacommunity) scales; and (2) evaluated the direction, magnitude, and precision of these effect estimates at both spatial scales. Methods We developed a multi-region community occupancy model to analyze 13 years (2005-2017) of amphibian monitoring data within the National Capital Region, a network of U.S. National Parks. Results Overall, we found a positive effect of park size and a negative effect of isolation on species richness at the park-level (i.e. metacommunity), and generally positive effects of wetland area, connectivity, and quality on species richness at the wetland-level (i.e. community), although parameter estimates varied among species. Covariate effects were less precise, but effects sizes were larger, at the local wetland-level as compared to the larger park-level scale. Conclusions Our analysis reveals how scale can mediate interpretation of results from scientific studies, which might help explain conflicting narratives concerning the impacts of fragmentation in the published literature. Our hierarchical framework can help managers and policymakers elucidate the relevant spatial scale(s) to target conservation efforts.