Date of Award

5-2009

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Legacy Department

Applied Economics

Advisor

Isengildina, Olga

Committee Member

Bridges , William

Committee Member

Kirby , Christopher

Committee Member

Nyankori , James

Abstract

The first paper examines the properties of the realized volatilities of US Dollar / Canadian Dollar spot exchange rate covering a time span of about three years and then the deseasonalized volatilities are estimated and forecasted using a fractionally-integrated model. The key feature of the realized volatilities is that they are model-free and also approximately measurement-error-free. Usually a U-shaped pattern of the intraday volatilities should be observed due to opening-closure effects in the global market. I do not see a typical U-shaped pattern in the intraday volatilities for US Dollar / Canadian Dollar. The reasons are given in this paper. I use ARFIMAX model to estimate and forecast the deseasonalized volatilities and the results are promising.
The second paper proposes a time series based trading strategy for 'pairs trading'. Pairs trading is one of the oldest statistical arbitrage strategies and has been proved to be successful on Wall Street. Most academic studies on pairs trading focus on pair selection or optimal threshold comparison. This is the first paper to introduce time series methodology into research of pairs trading. The dynamics of the spread between two stocks in a pair are tested and examined. A time series 'dynamic threshold method' is proposed in this paper and the trading strategy based on this method improves the excess return of traditional naïve pairs trading model significantly.

Included in

Economics Commons

Share

COinS