Statistics, Department of

The R Journal
Date of this Version
8-2016
Document Type
Article
Citation
The R Journal (August 2016) 8(1); Editor: Michael Lawrence
Abstract
Identifying the optimal number of clusters is a common problem faced by data scientists in various research fields and industry applications. Though many clustering evaluation techniques have been developed to solve this problem, the recently developed algorithm Progeny Clustering is a much faster alternative and one that is relevant to biomedical applications. In this paper, we introduce an R package progenyClust that implements and extends the original Progeny Clustering algorithm for evaluating clustering stability and identifying the optimal cluster number. We illustrate its applicability using two examples: a simulated test dataset for proof-of-concept, and a cell imaging dataset for demonstrating its application potential in biomedical research. The progenyClust package is versatile in that it offers great flexibility for picking methods and tuning parameters. In addition, the default parameter setting as well as the plot and summary methods offered in the package make the application of Progeny Clustering straightforward and coherent.
Included in
Numerical Analysis and Scientific Computing Commons, Programming Languages and Compilers Commons
Comments
Copyright 2016, The R Foundation. Open access material. License: CC BY 3.0 Unported