Longitudinal Clustering via Mixtures of Multivariate Power Exponential Distributions
| dc.contributor.advisor | McNicholas, Paul | |
| dc.contributor.author | Patel, Nidhi | |
| dc.contributor.department | Statistics | en_US |
| dc.date.accessioned | 2016-09-23T16:42:46Z | |
| dc.date.available | 2016-09-23T16:42:46Z | |
| dc.date.issued | 2016 | |
| dc.description.abstract | A mixture model approach for clustering longitudinal data is introduced. The approach, which is based on mixtures of multivariate power exponential distributions, allows for varying tail-weight and peakedness in data. In the longitudinal setting, this corresponds to more or less concentration around the most central time course in a component. The models utilize a modified Cholesky decomposition of the component scale matrices and the associated maximum likelihood estimators are derived via a generalized expectation-maximization algorithm. | en_US |
| dc.description.degree | Master of Science (MSc) | en_US |
| dc.description.degreetype | Thesis | en_US |
| dc.identifier.uri | http://hdl.handle.net/11375/20406 | |
| dc.language.iso | en | en_US |
| dc.subject | longitudinal data | en_US |
| dc.subject | model-based clustering | en_US |
| dc.subject | mixture models | en_US |
| dc.subject | power exponential distribution | en_US |
| dc.title | Longitudinal Clustering via Mixtures of Multivariate Power Exponential Distributions | en_US |
| dc.type | Thesis | en_US |