The Kelley model as an analysis of variance analogy: How far can it be taken?

摘要: Abstract Kelley's (1967, 1973) suggestion that the attribution process can be compared to statistical procedure of analysis variance (ANOVA) was investigated. More specifically, I examined whether person and entity attributions vary as a function different degrees covariation effect with respective cause, certainty about causal judgments is influenced by number observations. Unlike other studies in this field, complete rather than incomplete information relevant for ANOVA presented. In addition, numerical “raw” data “prepackaged” (summary) were given. Also, possible causes merely two levels (e.g., high vs low consensus) presented subjects. The comparison subjects' parameters revealed rated increasingly important an inasmuch variation attributable cause increased due alternative decreased. This relationship closely paralleled effect-size parameter ( η 2 ). more resistant new attributions. Certainty ratings uninfluenced manipulations.