Questions: How well do GIS-derived categorical variables (e.g., vegetation, soils, geology, elevation, geography, and physiography) separate plots based on community composition? How does the ability to distinguish plots by community composition vary with spatial scale, specifically number of patch types, patch size and spatial correlation? Both these questions bear on the effective use of stratifying variables in landscape ecology. Location: Arctic tundra; Bering Land Bridge National Preserve, northwestern Alaska, USA. Methods: We evaluated the strength of numerous alternative stratifying variables using the multi-response permutation procedure (MRPP). We also created groups based on lichen community composition, using cluster analyses, and evaluated the relationship between these groups and groupings within categorical variables using Mantel tests. Each test represents different measures of community separation, which were then evaluated with respect to each variable’s spatial characteristics. Results: We found each categorical variable derived from GIS separated lichen communities to some degree. Separation success ranged from strong (Alaska Subsections) to weak (Watersheds and Reindeer Ownership). Lichen community groups derived from cluster analysis demonstrated statistically significant relationships with 13 of the 17 categorical variables. Partialling out effects of spatial distance had little effect on these relationships. Conclusions: Greater number of patch types and larger average patch sizes contribute to optimal success in separating lichen communities; geographic distance did not appear to significantly alter separation success. Group distinctiveness or strength increased with more patch types or groups. Alternatively, congruence between lichen community types derived from cluster analysis and the 17 categorical variables was inversely related to patch size and spatial correlation.