Essays on Financial Market Volatility
(2011)- Abstract
- This thesis examines the volatility in the equity and short-term interest-rate markets, and the spillover from the short term interest rate market to the equity market. It consists of three papers and focuses on adapting and proposing models for the estimation and forecasting of financial market volatility. Chapter 1 gives a brief introduction to the parametric and nonparametric volatility models, as well as the estimation methods used in this thesis.
Chapter 2 applies a nonparametric smoothing technique to examine the volatility of the Chinese stock markets due to the unique characteristics of the Chinese markets. The results suggest that the leverage effect exists in the Chinese stock markets: Bad news does affect the return... (More) - This thesis examines the volatility in the equity and short-term interest-rate markets, and the spillover from the short term interest rate market to the equity market. It consists of three papers and focuses on adapting and proposing models for the estimation and forecasting of financial market volatility. Chapter 1 gives a brief introduction to the parametric and nonparametric volatility models, as well as the estimation methods used in this thesis.
Chapter 2 applies a nonparametric smoothing technique to examine the volatility of the Chinese stock markets due to the unique characteristics of the Chinese markets. The results suggest that the leverage effect exists in the Chinese stock markets: Bad news does affect the return volatility more than good news. Further, compared with the superior performance of the nonparametric model in the in-sample and out-of-sample forecast, the parametric models tend to overestimate the volatility process in turbulent periods and yield larger estimation errors. The results also suggest that the nonparametric model is a more appropriate tool to use in estimating the Chinese stock-return volatility than the parametric GARCH models.
Chapter 3 proposes a semi-parametric procedure to estimate the volatility of the weekly three-month U.S. Treasury bills. The new approach accommodates asymmetry, levels effect and serial dependence in the conditional variance and the volatility is estimated by a nonparametric smoothing technique. Results from our Monte Carlo simulation illustrate the robustness of the semiparametric approach when estimating short-rate volatility with misspecification in the short-rate drift function and the underlying innovation distribution. The empirical application to three-month U.S. Treasury bill yields suggests that the semiparametric estimation procedure provides superior in-sample and out-of-sample volatility forecasts compared to the widely used diffusion volatility models. Finally, we demonstrate that the semiparametric approach has pertinent implications for pricing long-dated and path-dependent interest-rate derivatives.
Chapter 4 examines the equity-return volatility and the spillover effects from short-term interest rates in the EMU area. The empirical study is carried out by estimating an extended Markov switching GJR-in-mean model with a Bayesian-based Markov chain Monte Carlo methodology. Our results suggest that two regimes exist in the EURO area stock markets; a high-mean low-variance (bull) market and a low-mean high-volatility (bear) market. Most of the EURO countries have the same regime-switching status between the bull and bear markets. Our results also suggest that bad news from unexpected stock returns (negative residuals from returns) has an asymmetrically larger effect on the returns and the volatility than good news has. Such an impact is larger in the bear market than in the bull market. As implied in the news-impact surface, we find that changes in short-term interest rates only significantly affect stock market volatility in the bear period in most of the EMU countries. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1890272
- author
- HOU, Ai Jun LU
- supervisor
- opponent
-
- Professor Johan, Knif, Hanken School of Economics, Vasa, Finland
- organization
- publishing date
- 2011
- type
- Thesis
- publication status
- published
- subject
- keywords
- Nonparametric GARCH model, News Impact Curve, Interest rate volatility, MCMC, Markov Switching, Chinese stock markets, EMU stock markets
- pages
- 131 pages
- defense location
- EC3:207
- defense date
- 2011-05-20 14:15:00
- language
- English
- LU publication?
- yes
- id
- bdc76b65-bb26-4ef6-962c-c1964182258c (old id 1890272)
- date added to LUP
- 2016-04-04 09:31:20
- date last changed
- 2018-11-21 20:53:41
@phdthesis{bdc76b65-bb26-4ef6-962c-c1964182258c,
abstract = {{This thesis examines the volatility in the equity and short-term interest-rate markets, and the spillover from the short term interest rate market to the equity market. It consists of three papers and focuses on adapting and proposing models for the estimation and forecasting of financial market volatility. Chapter 1 gives a brief introduction to the parametric and nonparametric volatility models, as well as the estimation methods used in this thesis. <br/><br>
Chapter 2 applies a nonparametric smoothing technique to examine the volatility of the Chinese stock markets due to the unique characteristics of the Chinese markets. The results suggest that the leverage effect exists in the Chinese stock markets: Bad news does affect the return volatility more than good news. Further, compared with the superior performance of the nonparametric model in the in-sample and out-of-sample forecast, the parametric models tend to overestimate the volatility process in turbulent periods and yield larger estimation errors. The results also suggest that the nonparametric model is a more appropriate tool to use in estimating the Chinese stock-return volatility than the parametric GARCH models. <br/><br>
Chapter 3 proposes a semi-parametric procedure to estimate the volatility of the weekly three-month U.S. Treasury bills. The new approach accommodates asymmetry, levels effect and serial dependence in the conditional variance and the volatility is estimated by a nonparametric smoothing technique. Results from our Monte Carlo simulation illustrate the robustness of the semiparametric approach when estimating short-rate volatility with misspecification in the short-rate drift function and the underlying innovation distribution. The empirical application to three-month U.S. Treasury bill yields suggests that the semiparametric estimation procedure provides superior in-sample and out-of-sample volatility forecasts compared to the widely used diffusion volatility models. Finally, we demonstrate that the semiparametric approach has pertinent implications for pricing long-dated and path-dependent interest-rate derivatives. <br/><br>
Chapter 4 examines the equity-return volatility and the spillover effects from short-term interest rates in the EMU area. The empirical study is carried out by estimating an extended Markov switching GJR-in-mean model with a Bayesian-based Markov chain Monte Carlo methodology. Our results suggest that two regimes exist in the EURO area stock markets; a high-mean low-variance (bull) market and a low-mean high-volatility (bear) market. Most of the EURO countries have the same regime-switching status between the bull and bear markets. Our results also suggest that bad news from unexpected stock returns (negative residuals from returns) has an asymmetrically larger effect on the returns and the volatility than good news has. Such an impact is larger in the bear market than in the bull market. As implied in the news-impact surface, we find that changes in short-term interest rates only significantly affect stock market volatility in the bear period in most of the EMU countries.}},
author = {{HOU, Ai Jun}},
keywords = {{Nonparametric GARCH model; News Impact Curve; Interest rate volatility; MCMC; Markov Switching; Chinese stock markets; EMU stock markets}},
language = {{eng}},
school = {{Lund University}},
title = {{Essays on Financial Market Volatility}},
url = {{https://lup.lub.lu.se/search/files/5346834/1894652.pdf}},
year = {{2011}},
}