Blake’s “A Poisson Tree” Statistically Climbed

Abstract

“A Poisson Tree” is an exemplary poem composed by William Blake in 1794. The present work encompasses a statistical study intensifying several features such as finding the appropriate probability distribution that fits the data corresponding to the number of words per line, word length, the number of vowels per stanza and the number of letters per line. Additionally, the various parts of speech used in the poem are studied and the pronoun is found to be used most. It is found that the number of words per line is distributed uniformly in the poem which is tested by Chi Square goodness of fit test. A Zero truncated Poisson distribution is found to be a good fit for the frequency distribution of word length. Binomial distribution turns out to be a good fit for the number of vowels per stanza in the poem. The number of letters per line is also distributed uniformly in the poem which is again tested by Chi Square goodness of fit test. The poem is following the rhythmic scheme AABB CCDD EEFF GGHH. The number of words between two successive rhythmic words can be dichotomized.