Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
30413.pdf (6.18 MB)
ETD Abstract Container
Abstract Header
A Study of Stochastic Processes in Natural and Social Sciences
Author Info
Liu, Zhiyuan
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=ucin153027399786377
Abstract Details
Year and Degree
2018, PhD, University of Cincinnati, Arts and Sciences: Physics.
Abstract
Bouchaud-Mezard network model and the combination of lognormal and Pareto distribution are two models that could give power-law tails. We applied these models to describe the distribution of human response time. We studied the scaling property of each model and used bootstrap method to obtain the confidence intervals of each shape related parameters. Then we studied the fundamental properties of the inverse Gamma stochastic process. We derived the relaxation time of the moments, the correlation function, and the relaxation time of the distribution. We find that the relaxation time of moments and correlation time of correlation function are characterized by the ratio of the coefficient of the drift part and square of the coefficient of the stochastic part. We also find that the distribution of the relaxation time of the distribution is inverse Gaussian. As to the Bouchaud-Mezard network model, we find that there is no steady state in a finite network because the average wealth changes with time. We also find that the distribution of the average wealth from different networks could be described by a lognormal distribution. At last, we studied one popular stock return model - Heston model. By using the product distribution and joint probability distribution function, we could get the distribution of the stock log-return in a short time, and it is consistent with results of the Heston model. We also applied the inverse Gamma process as the stochastic process of variance, and concluded that the Heston model was better.
Committee
Rostislav Serota, Ph.D. (Committee Chair)
F Paul Esposito, Ph.D. (Committee Member)
John Holden, Ph.D. (Committee Member)
Andrei Kogan, Ph.D. (Committee Member)
Michael Ma, Ph.D. (Committee Member)
Pages
102 p.
Subject Headings
Physics
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Liu, Z. (2018).
A Study of Stochastic Processes in Natural and Social Sciences
[Doctoral dissertation, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin153027399786377
APA Style (7th edition)
Liu, Zhiyuan.
A Study of Stochastic Processes in Natural and Social Sciences.
2018. University of Cincinnati, Doctoral dissertation.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=ucin153027399786377.
MLA Style (8th edition)
Liu, Zhiyuan. "A Study of Stochastic Processes in Natural and Social Sciences." Doctoral dissertation, University of Cincinnati, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=ucin153027399786377
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
ucin153027399786377
Download Count:
247
Copyright Info
© 2018, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.