The spatial distributions of agmatic complexes and other features thought to be associated with major crustal structures may be important sources of information about large‐scale structural patterns. However, attempts to incorporate these features into quantitative analyses of linear features have used arbitrary or inaccurate criteria to judge hypothetical geological relationships. In this paper, features of limited spatial extent are considered pointlike, and the concept of a probabilistic lattice point distribution is used to formulate a statistical method that leads to a quantitative and reproducible analysis of directional patterns based solely on the locations of the points. Thus this analysis is independent of linear patterns and provides a measure of the directional information intrinsic to point patterns. The procedure determines the most likely trends of structural anisotropies; Monte Carlo simulations of random point patterns provide a reference distribution from which confidence levels can be determined. Applications to published data for magmatic complexes, magnetic contour closures, and structural change points are used as examples. The results suggest that there has been a tendency to overestimate the amount of information available from point pattern