Authors

Riyu Yu

Type

Text

Type

Dissertation

Advisor

Rachev, Svetlozar | Mullhaupt, Andrew P | Xing, Haipeng | Xiao, Keli.

Date

2015-05-01

Keywords

Applied mathematics | 130-30 Fund, Fisher Information, Log Band Fraction, Long Only Portfolio, Low Volatility Strategy

Department

Department of Applied Mathematics and Statistics.

Language

en_US

Source

This work is sponsored by the Stony Brook University Graduate School in compliance with the requirements for completion of degree.

Identifier

http://hdl.handle.net/11401/77488

Publisher

The Graduate School, Stony Brook University: Stony Brook, NY.

Format

application/pdf

Abstract

Structured matrix plays an important role in statistics, especially in covariance estimation. Band fraction representation is one of the efficient structures for matrices. In this dissertation, we study the metric tensor for the band fraction representation for the covariance matrix. We propose a new structure, the log band fraction representation, which gives smaller information distance and Hellinger distance than factor model and band fraction representation. We apply the log band fraction estimation in the portfolio optimization problem. We propose our long only strategy and 130-30 strategy, which significantly outperform the benchmarks, i.e. | SPY, SPLV, and CSM. Transaction cost is considered in the portfolio construction process. The strategies proposed in this dissertation are fully investable. | 93 pages

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.