THE RELIABILITY OF OBSERVATIONAL DATA .1. THEORIES AND METHODS FOR SPEECH-LANGUAGE PATHOLOGY

Much research and clinical work in speech-language pathology depends o n the validity and reliability of data gathered through the direct obs ervation of human behavior. This paper reviews several definitions of reliability, concluding that behavior observation data are reliable if they, and the experimental conclusions drawn from them, are not affec ted by differences among observers or by other variations in the recor ding context. The theoretical bases of several methods commonly used t o estimate reliability for observational data are reviewed, with examp les of the use of these methods drawn from a recent volume of the Jour nal of Speech and Hearing Research (35,1992). Although most recent res earch publications in speech-language pathology have addressed the iss ue of reliability for their observational data to some extent, most re liability estimates do not clearly establish that the data or the expe rimental conclusions were replicable or unaffected by differences amon g observers. Suggestions are provided for improving the usefulness of the reliability estimates published in speech-language pathology resea rch.