Increasing concern about possible links between emissions of radon and certain types of malignant disease has led to local and regional surveys to measure radon concentrations in the soil and in dwellings. The spatial scale over which radon varies is usually unknown, and so efficient sampling schemes and methods of mapping cannot be selected. To determine the spatial scale of radon Variation in the English Midlands we have sampled radon in the soil using an unbalanced multistage scheme. The sampling design had seven stages representing distances between sampling points from 10 m to 7.5 km, increasing in a three-fold geometrical progression over an area of 225 km(2). The results indicate clearly that over 90% of the variation occurs over distances less than 10 m. This result has important implications for designing further surveys and for choosing a method of mapping.