The Statistical Study of Literary Vocabulary

ABCD accidents actual association average Bunyan cards cent Chapter characteristic Class cols columns compared comparison complete component considerable correlation corresponding counted course Dictionary distribution English entered error essay estimate evidence example expected experiment fact fall figures finally four four samples frequency Gerson give given illustration Imitatio included increase initial interest Latin less letters limit lines lower Macaulay mean measure method noted nouns occurring number of occurrences number of words observed obtained once percentage possible proportion question random range rank ratio reader reference relatively respective risk S₁ samples from Gerson samples from Thomas seems sense separate Showing the number shows similar simple single standard deviation statistical suggested Table taken Thomas à Kempis verbs vocabulary whole writings