ERA

Download the full-sized PDF of Estimating Sparse Graphical Models: Insights Through SimulationDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R3F766G1T

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Graduate Studies and Research, Faculty of

Collections

This file is in the following collections:

Theses and Dissertations

Estimating Sparse Graphical Models: Insights Through Simulation Open Access

Descriptions

Other title
Subject/Keyword
bootstrap
penalized log-likelihood
graphical model
glasso
estimate evaluation
Type of item
Thesis
Degree grantor
University of Alberta
Author or creator
Zhu, Yunan
Supervisor and department
Karunamuni, Rohana (Mathematical and Statistical Sciences)
Cribben, Ivor (Finance and Statistical Analysis)
Examining committee member and department
Karunamuni, Rohana (Mathematical and Statistical Sciences)
Yuan, Yan (Public Health)
Frei, Christoph (Mathematical and Statistical Sciences)
Jiang, Bei (Mathematical and Statistical Sciences)
Cribben, Ivor (Finance and Statistical Analysis)
Department
Department of Mathematical and Statistical Sciences
Specialization
Statistics
Date accepted
2015-09-30T09:22:04Z
Graduation date
2015-11
Degree
Master of Science
Degree level
Master's
Abstract
Graphical models are frequently used to explore networks among a set of variables. Several methods for estimating sparse graphs have been proposed and their theoretical properties have been explored. There are also several selection criteria to select the optimal estimated models. However, their practical performance has not been studied in detail. In this work, several estimation procedures (glasso, bootstrap glasso, adptive lasso, SCAD, DP-glasso and Huge) and several selection criteria (AIC, BIC, CV, ebic, ric and stars) are compared under various simulation settings, such as different dimensions or sample sizes, different types of data, and different sparsity levels of the true model structures. Then we use several evaluation criteria to compare the optimal estimated models and discuss in detail the superiority and deficiency of each combination of estimating methods and selection criteria.
Language
English
DOI
doi:10.7939/R3F766G1T
Rights
Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.
Citation for previous publication

File Details

Date Uploaded
Date Modified
2015-09-30T15:22:05.213+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (PDF/A)
Mime type: application/pdf
File size: 18248923
Last modified: 2016:06:24 17:53:52-06:00
Filename: Zhu_Yunan_201509_MSc.pdf
Original checksum: 63c4d6dfc5eab70bd8060350ae54a7f4
Well formed: true
Valid: true
File title: Zhu_Yunan_201509_MSc.pdf
File author: dongchi86
Page count: 167
Activity of users you follow
User Activity Date