Design-based and model-based inference in survey sampling: appreciating the difference

Model-based ideas in finite-population sampling have received renewed discu ssion in recent years. Their relationship to the classical ideas in samplin g theory do not appear to be universally well understood by samplers in app lied disciplines such as forestry, and ecology more broadly. The two infere ntial paradigms are constrasted, and explanations are supplemented with exa mples of discrete as well as continuously distributed populations. The trea tment of spatial structure is examined, also.