Sponsor
Portland State University. Department of Civil & Environmental Engineering
First Advisor
Thomas Schumacher
Term of Graduation
Summer 2023
Date of Publication
11-28-2023
Document Type
Thesis
Degree Name
Master of Science (M.S.) in Civil & Environmental Engineering
Department
Civil and Environmental Engineering
Language
English
Subjects
Censorship Considered, Censorship Ignored, Deck CR, NBI, Survival Analysis, TICR
DOI
10.15760/etd.3682
Physical Description
1 online resource (vi, 70 pages)
Abstract
Many sophisticated statistical models and analyses have been proposed to analyze datasets derived from the national bridge inventory (NBI). These objectives range from creating an understanding of the factors that drive the deterioration of bridge members to providing agencies with quantitative information for their maintenance and repair decisions. As these models become increasingly sophisticated and difficult to comprehend and implement, practicing engineers and owners are less likely to use them. Often, however, grouping data intuitively, for example, per a select structure type or condition rating and analyzing them using prescriptive statistics such as distribution fitting, does not only lie in their expertise but also all a practicing engineer or agency is interested in. This approach can be used to determine, for example, data-informed inspection intervals, which were proposed by some researchers a few years ago, or estimate the expected service life of a bridge member. This MS thesis extends previous work by employing distribution fitting where data censoring is considered appropriate to create so-called survival functions. The work presented focuses on concrete bridge decks in Oregon. Censoring is inherent to NBI data, and ignoring it introduces significant bias in the results. Specifically, if censoring is ignored, a member's durations in a particular condition rating (CR) are significantly underestimated. After a brief overview of NBI data and its censoring, distribution fitting where censoring is considered and ignored is compared. Step-by-step case studies are provided to illustrate how survival curves for concrete bridge decks are created and used to answer service life-related questions.
Rights
© 2023 Asmaa Almeshaileh
In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
Persistent Identifier
https://archives.pdx.edu/ds/psu/41116
Recommended Citation
Almeshaileh, Asmaa, "Probability Distribution Fitting for Censored Data: A Practical Guide for Survival Analysis of NBI Data for Concrete Bridge Decks in Oregon" (2023). Dissertations and Theses. Paper 6550.
https://doi.org/10.15760/etd.3682