2018 Volume 7 Issue 1 Pages 9-19
Reduced K-means is one of the methods used in cluster analysis. It simultaneously estimates both the dimensional axes of subspace that condense multivariate data and the cluster centroids in the subspace. I will point out the merit of this technique by showing an example in which it is applied to a large size of data obtained from a social survey. I compare the results from the Reduced K-means with those from the K-means method, as well as those from another method combining principal component analysis. Application of the Reduced K-means method requires the user to select the number of both dimensions and clusters. How to make such decisions will also be discussed based on the objective indices of cluster assessment.