Mathematical Model of Word Length on the Basis of the Cebanov-Fucks Distribution with Uniform Parameter Distribution
arXiv:cs/0102026
Abstract
The data on 13 typologically different languages have been processed using a two-parameter word length model, based on 1-displaced uniform Poisson distribution. Statistical dependencies of the 2nd parameter on the 1st one are revealed for the German texts and genre of letters.
4 pages, 1 table, 2 figures.Submitted to Conference on Informatics and Telecommunications, to be held in Sibirian State University of Telecommunications (Novosibirsk, Russia) in April, 2001