SEARCH

SEARCH BY CITATION

Abstract

The validity of a hypothesis test is partly determined by whether the assumptions underlying the test are satisfied. In the past, a preliminary analysis of the data has been suggested prior to the use of the statistical test. In this article, the authors describe several limitations of preliminary tests (e.g., influence on significance levels). Another strategy that uses theoretical knowledge in conjunction with prior empirical evidence and reason, prior to data collection, is described. © 2007 Wiley Periodicals, Inc. Psychol Schs 44: 495–502, 2007.