Cluster Analysis: A Toolbox for MATLAB

Association of childhood abuse with homeless women's social networks

“…The resulting proximity matrix was used in subsequent cluster analyses. The MATLAB Cluster Analysis toolbox used for these analyses first identifies the best linear arrangement of women based on their distances to each other (Hubert & Koehn, 2007; Hubert, Koehn, & Steinley, 2009). Then, the toolbox calculates partitions and objective functions for all possible clusters of women (from two to fifty-one) using k-means clustering algorithm, an approach that assigns women to the cluster with the closest mean.…”

Religious Congregations’ Involvement in HIV: A Case Study Approach

“…With the k - means procedure, the analyst specifies the number of clusters desired, and the algorithm determines the members of each cluster using the optimization approach described above. The analyst chooses the number of clusters (and their components) that best fit the data by comparing the relative change in optimization functions when moving between solutions with different numbers of clusters [56]. The cluster analysis was performed in a general computing and simulation software package [57] using a specialized cluster analysis toolbox [56].…”

“…The analyst chooses the number of clusters (and their components) that best fit the data by comparing the relative change in optimization functions when moving between solutions with different numbers of clusters [56]. The cluster analysis was performed in a general computing and simulation software package [57] using a specialized cluster analysis toolbox [56]. We visually display the clusters by mapping the positive match ties between the HIV activities using network analytic software [58], with the layout based on a “spring embedding” algorithm that places activities with the highest match scores to one another closest in the graph [55].…”

“…The layout of activities is based on a “spring embedding” algorithm that places activities with the highest match scores to one another closest in the graph [55]. (2) The three main clusters of HIV activities that tend to co-occur together were identified using a k - means optimization technique applied to the positive match scores [56]. We indicate the results of the k - means analysis on the graph by encircling the activities that fell within each cluster using overlaid shading…”

Examining Similarity Structure: Multidimensional Scaling and Related Approaches in Neuroimaging

“…Individual differences scaling is implemented in R with indscal() function in the SensoMineR package and the smacof package [82]. STATIS is implemented with statis() function in the ade4 package [83] in R. A highly versatile MATLAB toolbox for cluster analysis is available from Hubert et al [84]. …”