Abstract
The value of Shannon entropy for a given set of data depends on the class interval chosen to compute the relative frequency of each class. For three data sets, expressed in dimensional as well as nondimensional form, the entropy value was computed for different class-interval sizes. Entropy was found to decrease with increasing class interval as well as with increasing sampling interval. It is suggested that these intervals should be selected with care.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Shannon, C.E. 1948: A mathematical theory of communication. Bell System Technical Journal 27, 379–423 and 623–659
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Singh, V.P. Effect of class-interval size on entropy. Stochastic Hydrol Hydraul 11, 423–431 (1997). https://doi.org/10.1007/BF02427927
Issue Date:
DOI: https://doi.org/10.1007/BF02427927