To investigate the relative importance of long-distance dispersal vs. diffusion in the invasion of a nonnative plant, we used age structure to infer the contribution to recruitment of external propagule rain vs. within-population reproduction. We quantified the age structure of 14 populations of Amur honeysuckle in a landscape where it recently invaded, in Darke County, OH. We sampled the largest honeysuckle individuals in each population (woodlots), and aged these by counting annual rings in stem cross sections. Individuals in the oldest four 1-yr age classes are assumed to be from external recruitment, given the minimum age at which shrubs reproduce. We used these recruitment rates to model external recruitment over the next 5 yr and used observed age structures to estimate total recruitment. We used the difference between total and external recruitment to infer the rate of internal recruitment. Our findings indicate that recruitment from within the population is of about the same magnitude as immigration in the fifth to seventh year after population establishment, but by years 8 to 9 internal recruitment dominates. At the landscape scale, the temporal-spatial pattern of population establishment supports a stratified dispersal model, with the earliest populations establishing in widely spaced woodlots, about 4 km from existing populations, and these serving as “nascent foci” for diffusion to nearby woodlots. Understanding the relative importance of long-distance dispersal vs. diffusion will inform management, e.g., whether it is more effective to scout for isolated shrubs or remove reproducing shrubs at the edge of invaded areas.