Distributions of different parts of speech in different parts of a text and in different texts by Hemlata Pan

The present work is an attempt in the direction of predicting sequences of building blocks of communication, the parts of speech, in any text. Five novels and five short stories of English language have been tagged under four different treatments and then statistical distributions of the parts of speech have been obtained. The goodness of fit of the distributions has been testified by χ2 -test while the validation of the four different treatments has been done by the application of random block design and completely randomized design of experiments, under the assumption that the mean of distribution scores for applied treatments is same for different parts and sub-parts of the POS. The mean scores of distributions of different POS have been also compared by random block design.