Localized quantile regression of realized volatility

Koralage, Janaki (2019) Localized quantile regression of realized volatility. Masters thesis, Memorial University of Newfoundland.

[img] [English] PDF - Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.

Download (3MB)


Volatility is a financial term that measures the dispersion of asset returns. Calculating and predicting volatility are not simple, but there are several well-known models for determining the volatility of assets. In recent years, researchers have been interested in developing statistical methods to model financial volatility, and new concepts have been applied to achieve better results. Quantile regression is another area gaining increased attention in the analysis of financial data. In this thesis, we propose a new quantile regression model for measuring the volatility of financial assets called the localized quantile regression model. As the name suggests, the proposed model is a local model rather than a global model. It takes care of possible structural changes and makes predictions of volatility more reliable. The initial step in this approach is to identify the longest interval of homogeneity. Identifying this interval of homogeneity involves a sequential testing procedure. After identifying intervals, we can apply quantile regression for each homogeneous time interval. The main advantage of this method is that it does not require any distributional assumptions. Simulation studies are carried out to investigate the performance of the proposed method. Results obtained from the simulation study show that the localized quantile regression model is appropriate for modeling the volatility of financial assets.

Item Type: Thesis (Masters)
URI: http://research.library.mun.ca/id/eprint/13746
Item ID: 13746
Additional Information: Includes bibliographical references (pages 48-49).
Keywords: Quantile Regression, Volatility, Realized Volatility
Department(s): Science, Faculty of > Mathematics and Statistics
Date: January 2019
Date Type: Submission
Library of Congress Subject Heading: Quantile regression; Stock price forecasting--Mathematical models

Actions (login required)

View Item View Item


Downloads per month over the past year

View more statistics