skip to main content

PERHITUNGAN VALUE AT RISK DENGAN PENDEKATAN THRESHOLD AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY-GENERALIZED EXTREME VALUE

Mutik Dian Prabaning Tyas  -  Departemen Statistika, Fakultas Sains dan Matematika, Universitas Diponegoro, Indonesia
*Di Asih I Maruddani  -  Departemen Statistika, Fakultas Sains dan Matematika, Universitas Diponegoro, Indonesia
Rita Rahmawati  -  Departemen Statistika, Fakultas Sains dan Matematika, Universitas Diponegoro, Indonesia
Open Access Copyright (c) 2019 MEDIA STATISTIKA under http://creativecommons.org/licenses/by-nc-sa/4.0.

Citation Format:
Abstract

Stock is the most popular type of financial asset investment. Before buying a stock, an investor must estimate the risks which will be received. Value at Risk (VaR) is one of the methods that can be used to measure the level of risk. When investing in stock, if an investor wants to earn high returns, then he must be prepared to face higher risks. Most of stock return data have volatility clustering characteristic or there are cases of heteroscedasticity and the distribution of stock returns has heavy tail. One of the time series models that can be used to overcome the problem of heteroscedasticity is the ARCH/GARCH model, while the method for analyzing heavy tail data is Extreme Value Theory (EVT). In this study used an asymmetrical ARCH model with the Threshold ARCH (TARCH) and EVT methods with Generalized Extreme Value (GEV) to calculate VaR of the stock return from PT Bumi Serpong Damai Tbk for the period of September 2012 to October 2018. The best chosen model is AR([3])–TARCH(1). At the 95% confidence level, the maximum loss an investor will be received within the next day by using the TARCH-GEV calculation is 0.18%.

Fulltext View|Download

Article Metrics:

Last update:

No citation recorded.

Last update: 2024-11-03 00:14:00

No citation recorded.