Premium
Commentary on “Validating the Interpretations and Uses of Test Scores”
Author(s) -
Brennan Robert L.
Publication year - 2013
Publication title -
journal of educational measurement
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.917
H-Index - 47
eISSN - 1745-3984
pISSN - 0022-0655
DOI - 10.1111/jedm.12001
Subject(s) - argument (complex analysis) , generalization , computer science , test (biology) , interpretation (philosophy) , optimism , extrapolation , artificial intelligence , psychology , epistemology , mathematics , social psychology , statistics , paleontology , philosophy , biochemistry , chemistry , biology , programming language
Kane's paper “Validating the Interpretations and Uses of Test Scores” is the most complete and clearest discussion yet available of the argument‐based approach to validation. At its most basic level, validation as formulated by Kane is fundamentally a simply‐stated two‐step enterprise: (1) specify the claims inherent in a particular interpretation and/or use of test scores (IUA); and (2) provide an evaluation of the claims (validity argument). Kane discusses four types of inferences that provide a scaffolding for addressing these two arguments: scoring, generalization, extrapolation, and decision rules. Decision rules, in particular, are closely related to consequences, which loom large in the argument‐based approach to validation. The present commentary on Kane's paper attempts to simplify some of his discussions, while expanding others. The author suggests that Kane's argument‐based approach to validation offers by far the best current basis for optimism about improvements in validation.