Tsogo L, Masson M H, Bardot A
Multivariate Behav Res. 2000 Jul 1;35(3):307-19. doi: 10.1207/S15327906MBR3503_02.
Given a set of dissimilarities data between n objects, multidimensional scaling is the problem of reconstructing a geometrical pattern of these objects, using n points, so that between-points distance corresponds to between-objects dissimilarity. Often, the collection of input data requires rating the dissimilarities between all n(n - 1)/2 possible pairs of stimuli. When the number of stimuli is large, say n $ 30, the number of pairs to be compared becomes very large and the similarity task inefficient. Hence a question of major importance is how to increase the efficiency of the similarity task while maintaining satisfactory scaling solutions. This article reviews the main similarity task methods suitable for a large objects set.
给定一组n个对象之间的差异数据，多维缩放是使用n个点重建这些对象的几何模式的问题，使得点与点之间的距离对应于对象与对象之间的差异。通常，输入数据的集合需要对所有n(n - 1)/2个可能的刺激对之间的差异进行评级。当刺激的数量很大时，比如说n≥30，需要比较的对数会变得非常大，相似性任务效率低下。因此，一个至关重要的问题是如何在保持令人满意的缩放解决方案的同时提高相似性任务的效率。本文回顾了适用于大型对象集的主要相似性任务方法。
