Premium
Reliability theory and clinical psychology
Author(s) -
Payne Robert W.
Publication year - 1989
Publication title -
journal of clinical psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.124
H-Index - 119
eISSN - 1097-4679
pISSN - 0021-9762
DOI - 10.1002/1097-4679(198903)45:2<351::aid-jclp2270450228>3.0.co;2-w
Subject(s) - reliability (semiconductor) , standard error , psychology , standard deviation , psychometrics , statistics , test (biology) , psychological testing , range (aeronautics) , observational error , test score , standard score , test theory , clinical psychology , econometrics , mathematics , standardized test , engineering , paleontology , power (physics) , physics , quantum mechanics , biology , aerospace engineering
Psychologists who report test results usually ignore the published data on the reliability of the test. When reliability is taken into account, the standard error of measurement is used to estimate the magnitude of the range around the observed score in which the true score is most likely to occur. It is assumed that the observed score is the best available estimate of the true score and that the standard error of measurement is the standard deviation of possible true scores around this observed score that could result from errors of measurement. Most textbooks of psychometrics notwithstanding, neither of these popular beliefs is correct. The correct procedure for estimating the most probable true score and the range of error associated with it is described, and the implications for psychological report writing are discussed.