Abstract

The price process in electronic markets is one prototypical example of a stochastic process, and it has historically be fitted and analyzed using different stochastic models such as Levy processes, diffusions, and SDEs (stochastic differential equations). In this thesis, we analyze Microsoft stock data in 2014-11-03 with the goal of studying the presence of jumps based on Limit Order Book (LOB) data. To this end, we divide the whole day’s data into many consecutive intervals and proceed to apply a jump detection method to identify the intervals that could potentially have jumps. After obtaining the intervals with potential jumps, we zoom in these intervals and compare them in order to characterize their features. More specifically, we analyze the price LOB data from both the traditional side and the statistical side, and our aim is that try to identify statistical differences between the intervals with jumps and without any jump, and then give evidence to support this jump detection method and conjecture reasons for the appearance of sharp price changes in small intervals.

Committee Chair

Jose E. Figueroa-Lopes

Committee Members

Jose E. Figueroa-Lopes,Todd Kuffner

Comments

Permanent URL: https://doi.org/10.7936/K70Z71QC

Degree

Master of Arts (AM/MA)

Author's Department

Mathematics

Author's School

Graduate School of Arts and Sciences

Document Type

Thesis

Date of Award

Spring 5-2017

Language

English (en)

Download

Included in

Mathematics Commons

Share

COinS