Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List

Full text release has been delayed at the author's request until August 31, 2026

ETD Abstract Container

Abstract Header

Accelerating Bootstrap Resampling using Two-Step Poisson-Based Approximation Schemes

Gula, Govardhan
http://rave.ohiolink.edu/etdc/view?acc_num=ysu1714404009447901

Abstract Details

, Master of Computing and Information Systems, Youngstown State University, Department of Computer Science and Information Systems.
Bootstrap sampling serves as a cornerstone in statistical analysis, providing a robust method to evaluate the precision of sample-based estimators. As the landscape of data processing expands to accommodate big data, approximate query processing (AQP) emerges as a promising avenue, albeit accompanied by challenges inaccurate assessment. By leveraging bootstrap sampling, the errors of sample-based estimators in AQP can be effectively evaluated. However, the implementation of bootstrap sampling encounters obstacles, particularly in the computation-intensive resampling procedure. This thesis embarks on an exploration of various resampling methods, scrutinizing five distinct approaches: On Demand Materialization (ODM) Method, Conditional Binomial Method (CBM), Naive Method, Two-Step Poisson Random (TSPR), and Two-Step Poisson Adaptive (TSPA). Through rigorous evaluation and comparison of the execution time for each method, this thesis elucidates their relative efficiencies and contributions to AQP analyses within the realm of big data processing. Furthermore, this research contributes to the broader understanding of resampling techniques in statistical analysis, offering insights into their computational complexities and implications for big data analytics. By addressing the challenges posed by AQP in the context of bootstrap sampling, this thesis seeks to advance methodologies for accurate assessment in the era of big data processing.
Feng Yu, PhD (Advisor)
Lucy Kerns, PhD (Committee Member)
Alina Lazar, PhD (Committee Member)
40 p.
Computer Science; Engineering; Information Systems; Information Technology; Mathematics
On Demand Materialization; ODM; Conditional Binomial Method; CBM; Naive Method; Two-Step Poisson Random; TSPR; Two-Step Poisson Adaptive; TSPA; AQP; Approximate Query Processing; Bootstrap Sampling; resampling methods; multinomial distribution; Poisson distribution; GSL; GNU Compiler Collection

Recommended Citations

Citations

  • Gula, G. (2024). Accelerating Bootstrap Resampling using Two-Step Poisson-Based Approximation Schemes [Master's thesis, Youngstown State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1714404009447901

    APA Style (7th edition)

  • Gula, Govardhan. Accelerating Bootstrap Resampling using Two-Step Poisson-Based Approximation Schemes. 2024. Youngstown State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ysu1714404009447901.

    MLA Style (8th edition)

  • Gula, Govardhan. "Accelerating Bootstrap Resampling using Two-Step Poisson-Based Approximation Schemes." Master's thesis, Youngstown State University, 2024. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1714404009447901

    Chicago Manual of Style (17th edition)

ysu1714404009447901
© 2024, all rights reserved.
This open access ETD is published by Youngstown State University and OhioLINK.