Three essays on applying structure analysis in financial econometrics

Author: 
Date created: 
2018-11-23
Identifier: 
etd20003
Keywords: 
Network analysis
Wavelet decomposition
Forecasting
Financial market
Abstract: 

This thesis is composed of three essays on applying different structure analyses in financial econometrics. The first chapter, entitled "Application of Wavelet-based Structures in Time-Series Index Forecasting", is based on a joined work with Ramazan Gencay and M. Ege Yazgan, which is published in Economics Letters in 2017. This essay explores the potential of wavelet-based multiresolution analysis in forecasting. A hierarchical structure for a single time series index is defined and estimated in frequency domain, based on which a forecast combination technique is applied to achieve an improvement in forecast accuracy. The second chapter, entitled "Application of Network Structures in Stock Return Volatility Forecasting", is based on a joined work with Xiao Yu and Ramazan Gencay. This essay explores the potential of network analysis in forecasting stock return volatility. A customer and supplier network structure is identified and incorporated in the usual reduced form stock return volatility model. Results show that there is a propagation dynamic of stock return volatility along supply chain, and incorporating customer channel improves the accuracy of volatility forecasting. The third chapter, entitled "Application of Network Structures in Mutual Fund Performance Forecasting", is based on a joined work with Ramazan Gencay, which is published in Singapore Economic Review in 2018. This essay explores the relationship between mutual fund performance persistence and the network structure of mutual funds. By constructing a network of mutual funds based on the commonality of their stock holdings, we can identify mutual funds that are more likely to possess momentum in performance.

Document type: 
Thesis
Rights: 
This thesis may be printed or downloaded for non-commercial research and scholarly purposes. Copyright remains with the author.
File(s): 
Senior supervisor: 
Ramazan Gencay
Department: 
Arts & Social Sciences: Department of Economics
Thesis type: 
(Thesis) Ph.D.
Statistics: