Burcu Aydin

A principal component analysis for trees

The active field of Functional Data Analysis (about understanding the variation in a set of curves) has been recently extended to Object Oriented Data Analysis, which considers populations of more general objects. A particularly challenging extension of this set of ideas is to populations of tree-structured objects. We develop an analog of Principal Component Analysis for trees, based on the notion of tree-lines, and propose numerically fast (linear time) algorithms to solve the resulting optimization problems. The solutions we obtain are used in the analysis of a data set of 73 individuals, where each data object is a tree of blood vessels in one persons brain.

Visualizing the structure of large trees

This study introduces a new method of visualizing complex tree structured objects. The usefulness of this method is illustrated in the context of detecting unexpected features in a data set of very large trees. The major contribution is a novel two-dimensional graphical representation of each tree, with a covariate coded by color. The motivating data set contains three dimensional representations of brain artery systems of 105 subjects. Due to inaccuracies inherent in the medical imaging techniques, issues with the reconstruction algo- rithms and inconsistencies introduced by manual adjustment, various discrepancies are present in the data. The proposed representation enables quick visual detection of the most common discrepancies. For our driving example, this tool led to the modification of 10% of the artery trees and deletion of 6.7%. The benefits of our cleaning method are demonstrated through a statistical hypothesis test on the effects of aging on vessel structure. The data cleaning resulted in improved significance levels.

Dimension reduction in principal component analysis for trees

The statistical analysis of tree structured data is a new topic in statistics with wide application areas. Some Principal Component Analysis (PCA) ideas have been previously developed for binary tree spaces. These ideas are extended to the more general space of rooted and ordered trees. Concepts such as tree-line and forward principal component tree-line are redefined for this more general space, and the optimal algorithm that finds them is generalized. An analog of the classical dimension reduction technique in PCA for tree spaces is developed. To do this, backward principal components, the components that carry the least amount of information on tree data set, are defined. An optimal algorithm to find them is presented. Furthermore, the relationship of these to the forward principal components is investigated, and a path-independence property between the forward and backward techniques is proven. These methods are applied to a brain artery data set of 98 subjects. Using these techniques, the effects of aging to the brain artery structure of males and females is investigated. A second data set of the organization structure of a large US company is also analyzed and the structural differences across different types of departments within the company are explored.

A Nonparametric Regression Model With Tree-Structured Response

Developments in science and technology over the last two decades has motivated the study of complex data objects. In this article, we consider the topological properties of a population of tree-structured objects. Our interest centers on modeling the relationship between a tree-structured response and other covariates. For tree-structured objects, this poses serious challenges since most regression methods rely on linear operations in Euclidean space. We generalize the notion of nonparametric regression to the case of a tree-structured response variable. In addition, we develop a fast algorithm and give its theoretical justification. We implement the proposed method to analyze a dataset of human brain artery trees. An important lesson is that smoothing in the full tree space can reveal much deeper scientific insights than the simple smoothing of summary statistics. This article has supplementary materials online.

A Copula Approach to Inventory Pooling Problems with Newsvendor Products

This study focuses on the inventory pooling problem under the newsvendor framework. The specific focus is the change in inventory levels when product inventories are pooled. We provide analytical conditions under which an increase (or decrease) in the total inventory levels should be expected. We introduce the copula framework to model a wide range of dependence structures between pooled demands, and provide a numerical study that gives valuable insights into the effects of marginal demand distributions and dependence structure on inventory pooling decisions.