作者: Tsang , Williams
DOI: 10.2307/41703478
关键词:
摘要: In "Generalizing Generalizability in Information Systems Research," Lee and Baskerville (2003) try to clarify generalization classify it into four types. Unfortunately, their account is problematic. We propose repairs. Central among these our balance-of-evidence argument that we should adopt the view Hume's problem of induction has a solution, even if do not know what is. build upon this by proposing an alternative classification induction. There are five types generalization: (1) theoretical, (2) within-population, (3) cross-population, (4) contextual, (5) temporal, with theoretical being across empirical levels rest within level. Our also includes two kinds inductive reasoning belong domain generalization. then discuss implications for information systems research.