CHARACTERIZING UNCERTAINTY IN LOW-DIMENSIONAL MODEL SELECTION

Kissel, Nicholas (2019) CHARACTERIZING UNCERTAINTY IN LOW-DIMENSIONAL MODEL SELECTION. Master's Thesis, University of Pittsburgh. (Unpublished)

Preview

PDF Download (1MB) | Preview

Abstract

In the context of big and often high-dimensional data, valid procedures for assessing variable importance and identifying accurate model representations are essential tools, especially in the presence of substantial instability. Instead of seeking to find only a single set of covariates that form the empirically optimal model, we propose an automated procedure for identifying an entire collection of stable and predictively similar models. Within each iterate of the selection method, we develop a procedure to identify covariates that are predictively similar with regard to a chosen loss function, thereby providing multiple options as to which covariate should be added to the final model. By construction, our procedure acts a wrapper method that can be applied to any statistical or machine learning technique. Furthermore, we provide a natural and intuitive graphical display of these model paths that makes apparent potential underlying relationships between covariates as well as the relative importance of the covariates selected.

---

Share

Citation/Export:	Select format... Citation - Text Citation - HTML Endnote BibTex Dublin Core OpenURL MARC (ISO 2709) METS MODS EP3 XML Reference Manager Refer
Social Networking:	Share |

---

Details

Item Type:	University of Pittsburgh ETD
Status:	Unpublished
Creators/Authors:	Creators Email Pitt Username ORCID Kissel, Nicholas njk51@pitt.edu njk51
ETD Committee:	Title Member Email Address Pitt Username ORCID Committee Chair Mentch, Lucas lkm31@pitt.edu lkm31 Committee Member Iyengar, Satish ssi@pitt.edu ssi Committee Member Cheng, Yu yucheng@pitt.edu yucheng
Date:	19 June 2019
Date Type:	Publication
Defense Date:	5 April 2019
Approval Date:	19 June 2019
Submission Date:	12 April 2019
Access Restriction:	3 year -- Restrict access to University of Pittsburgh for a period of 3 years.
Number of Pages:	43
Institution:	University of Pittsburgh
Schools and Programs:	Dietrich School of Arts and Sciences > Statistics
Degree:	MS - Master of Science
Thesis Type:	Master's Thesis
Refereed:	Yes
Uncontrolled Keywords:	Model Selection, Forward Selection, Stability Selection
Date Deposited:	19 Jun 2019 20:27
Last Modified:	19 Jun 2022 05:15
URI:	http://d-scholarship.pitt.edu/id/eprint/36788

Available Versions of this Item

• CHARACTERIZING UNCERTAINTY IN LOW-DIMENSIONAL MODEL SELECTION. (deposited 19 Jun 2019 20:27) [Currently Displayed]

---

Metrics

Monthly Views for the past 3 years

Plum Analytics

---

Actions (login required)

View Item