Practical implications of design-based sampling inference for thematic mapaccuracy assessment

Sampling inference is the process of generalizing from sample data to make statements or draw conclusions about a population. Design-based inference i s the inferential framework commonly invoked when sampling techniques are u sed in thematic map accuracy assessment. The conceptual basis of design-bas ed inference is described, followed by discussion of practical implications of design-based inference, including (1) the population to which the infer ences apply, (2) estimation formulas and their justification, (3) interpret ation of accuracy measures, (4) representation of variability, (5) effect o f spatial correlation, and (6) role of probability sampling. Design-based i nference is contrasted with model-based inference, another inferential fram ework frequently invoked in statistics. (C)Elsevier Science Inc., 2000.