|Title||Unsupervised Learning on the Health and Retirement Study using Geometric Data Analysis|
|Publication Type||Conference Paper|
|Year of Publication||2019|
|Authors||Sanchez-Arias, R, Batista, RW|
|Conference Name||2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)|
|Conference Location||Boca Raton, FL, USA|
|Keywords||Aging, Sociology, Data analysis, dimensionality reduction, Economics, Education, hierarchical clustering, multiple correspondence analysis, Retirement, Statistics|
A geometric data analysis that builds a lower dimensional representation of both individuals and measured variables is used to detect and represent underlying structures in the US Health and Retirement Study, a longitudinal survey of a representative sample of Americans over age 50 that captures information on how changing health interacts with social, economic, and psychological factors and retirement decisions. Multiple correspondence analysis is performed on a subset of the survey responses, creating a lower dimensional representation of the respondents and their response patterns, and a hierarchical clustering method is applied to test and validate specific structures in this population study.