A Comparison of Clustering and Missing Data Methods for Health Sciences

TL;DR

This paper compares clustering methods for health data with missing values, demonstrating that spectral clustering combined with compressive sensing outperforms traditional approaches in accuracy and data completion.

Contribution

It introduces the use of spectral clustering with matrix completion via compressive sensing for health data, showing improved performance over standard methods.

Findings

Lower misclassification rates with proposed methods

Better matrix completion performance

Spectral clustering leverages high-dimensional data properties

Abstract

In this paper, we compare and analyze clustering methods with missing data in health behavior research. In particular, we propose and analyze the use of compressive sensing's matrix completion along with spectral clustering to cluster health related data. The empirical tests and real data results show that these methods can outperform standard methods like LPA and FIML, in terms of lower misclassification rates in clustering and better matrix completion performance in missing data problems. According to our examination, a possible explanation of these improvements is that spectral clustering takes advantage of high data dimension and compressive sensing methods utilize the near-to-low-rank property of health data.