作者: Joseph L. Zinnes , David B. MacKay
DOI: 10.1016/S0166-4115(08)60236-8
关键词: Probabilistic logic 、 Social psychology 、 Multidimensional analysis 、 Multivariate normal distribution 、 Statistical model 、 Simple (abstract algebra) 、 Preference (economics) 、 Maximum likelihood 、 Variance (accounting) 、 Statistics 、 Psychology
摘要: A probabilistic multidimensional model is described for analyzing preference ratio judgments. This combines the unfolding of Coombs with Hefner, in which stimuli and individuals are represented by multivariate normal distributions. simple procedure approximating maximum likelihood estimates location variance parameters model. Two simulations show how well this works, especially when there considerable variability data.