Performance of Philippine equity portfolios under value-at-risk and expected shortfall frameworks

This study is an attempt to discover the effects of implementing risk constraints to portfolio value as a part of a prudent market risk management. Aside from value-at-risk as a constraint, the plausibility of using the Expected Shortfall is also explored to see whether it will be a better alternati...

Full description

Saved in:
Bibliographic Details
Main Author: Sewane, Eden S.
Format: text
Language:English
Published: Animo Repository 2015
Online Access:https://animorepository.dlsu.edu.ph/etd_masteral/4967
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
Language: English
Description
Summary:This study is an attempt to discover the effects of implementing risk constraints to portfolio value as a part of a prudent market risk management. Aside from value-at-risk as a constraint, the plausibility of using the Expected Shortfall is also explored to see whether it will be a better alternative to VaR. The risk limits are computed under two distribution assumptions. Assets included in the portfolios are limited to stocks listed in the Philippine Stock Exchange (PSE) and 10-year government bond as a risk-free asset. Stocks included in the portfolios are selected using: (1) Sharpe ratio (2) Momentum and, (3) Contrarian. Peak-Over-Threshold (POT) methodology is used in computing Value at Risk and Expected Shortfall under the Generalized Pareto Distribution assumption. Portfolio performance was evaluated using conditional and unconditional measures to take into account available public information that could interpose to the portfolio value. Ordinary Least Squares methodology was used to estimate the alphas from the performance evaluation models and t-statistics to determine the significance thereof. This research discovered that Expected Shortfall is better than Value at Risk in protecting portfolio returns under the assumption of normality, while VaR is better in the assumption of Generalized Pareto Distribution. Lastly, the assumption of GPD provides more accurate forecast of market risk.