Are Clusterings of Multiple Data Views Independent?

• Activity Number: 284 - ASA Biometrics Section JSM Travel Awards (II)
• Type: Topic Contributed
• Date/Time: Tuesday, July 30, 2019 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Lucy Gao* and Daniela Witten and Jacob Bien
• Companies: University of Washington and University of Washington and University of Southern California
• Keywords: Data integration; Hypothesis testing; Model-based clustering; Multiple-view data

Abstract

In the Pioneer 100 (P100) Wellness Project (Price and others, 2017), multiple types of data are collected on a single set of participants at multiple timepoints to optimize wellness. One way to do this is to identify subgroups, or clusters, among the participants, and then to tailor personalized health recommendations to each subgroup. It is tempting to cluster the participants using all of the data types and timepoints. However, clustering the participants based on multiple data views implicitly assumes that a single underlying clustering of the participants is shared across all data views. In this paper, we seek to evaluate the assumption that there is some underlying relationship among the clusterings from the different data views, by asking the question: are the clusters within each data view dependent or independent? We develop a new test for answering this question, which we apply to three distinct types of data, across two distinct timepoints, from the P100 study. We find that while the subgroups of the participants based on any single data type seem to be dependent across time, the subgroups of the participants based on different data types do not appear associated.