The statistical study of plant distribution patterns using a grid of quadrats

The statistical theory of the method of analysis of variance on a grid of contiguous quadrats is examined and the results from theoretical models for plant communities giving rise to non-randomness in the field discussed. Some field data are analysed and the theoretical and practical results correlated to determine the efficiency of the method as a practical technique. The large element that chance variation plays in practice makes it essential for several samples of the same community to be taken so that real and chance effects can be distinguished. A knowledge of the morphology of the species under consideration is desirable, for then some idea of the expected analysis of variance is available and there should be no confusion between different models.