Archived

This content is available here for research, reference, and/or recordkeeping.

Author ORCID Identifier

https://orcid.org/0009-0004-8464-8855

Date Available

5-14-2028

Year of Publication

2026

Document Type

Doctoral Dissertation

Degree Name

Doctor of Philosophy (PhD)

College

Arts and Sciences

Department/School/Program

Statistics

Faculty

Derek S. Young

Abstract

Confidence intervals and prediction intervals are widely known and commonly used in statistical analysis. Confidence intervals provide bounds for an unknown population mean, while prediction intervals provide bounds for a future observation, each with a specified level of confidence. In many practical situations, however, the goal is to construct an interval or region that contains at least a specified proportion of the population with a given level of confidence, and such an interval is called a tolerance interval (TI). This dissertation, titled \textit{Application of Tolerance Intervals in Applied Data Analysis}, examines the role of tolerance intervals as practical tools for inference, data quality assessment, and reliability analysis in survey data analysis. The first project develops tolerance intervals (TIs) for randomized response techniques (RRTs). RRTs are used to estimate population proportions for sensitive characteristics. The second project develops a new methodology for multivariate ratio edits using parametric and nonparametric TIs, providing interpretable alternatives to traditional Mahalanobis-based ratio editing methods. The third project develops three approaches for constructing TIs for future estimates of the intraclass correlation coefficient (ICC), with an emphasis on reliability studies.

Digital Object Identifier (DOI)

https://doi.org/10.13023/etd.2026.183

Archival?

Archival

Download

Available for download on Sunday, May 14, 2028

Contact Author

Share

COinS