Inference for correlation-based hierarchical clustering of variables
Abstract/Contents
- Abstract
- In this dissertation, we consider the clustering of variables based on their pairwise absolute sample correlations, with a focus on hierarchical clustering procedures. While these procedures have existed for quite some time, statistical guarantees on the resulting clusters of variables are not available. We construct test statistics and corresponding null distributions for each merge in the clustering tree. We develop new multiple testing procedures to combine these stepwise results into an adaptive cutting procedure to select a set of clusters from the hierarchical tree and attach a statistical guarantee. As part of this work, we also develop new distributional results for the large order statistics of sample correlations between many spherically distributed variables.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2014 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Grazier-G'Sell, Maxwell Jacob |
|---|---|
| Associated with | Stanford University, Department of Statistics. |
| Primary advisor | Tibshirani, Robert |
| Thesis advisor | Tibshirani, Robert |
| Thesis advisor | Hastie, Trevor |
| Thesis advisor | Taylor, Jonathan |
| Advisor | Hastie, Trevor |
| Advisor | Taylor, Jonathan |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Maxwell Jacob Grazier-G'Sell. |
|---|---|
| Note | Submitted to the Department of Statistics. |
| Thesis | Thesis (Ph.D.)--Stanford University, 2014. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2014 by Maxwell Jacob Grazier-G'Sell
Also listed in
Loading usage metrics...