Reliability in the Determination of Speech Discrimination

Abstract

A theoretical statistical analysis, which takes into consideration the random effect in the determination of speech discrimination, demonstrates that binomial distribution can be used to assess the reliability of the result. A clinical study supports the theory, which shows that reliability depends on the discrimination of the patient, length of word list and upon the character of the word material. The standard deviation of the discrimination value at repeated measurements on the same patient is, in theory, proportionally inverse to the square root of the number of words in the list. Curves with confidence intervals for the discrimination values obtained are presented and also diagrams indicating when two different discrimination results deviate significantly from each other. Curtailment of a 50-word list to a 25-word list is recommended only in those cases where the patient has at maximum one mistake in these 25 words. In order that reliability can be estimated, the length of the word list used always should be given, together with the discrimination result.