Estimation of Exchange Rate Volatility using APARCH-type Models: A Case Study of Indonesia (2010–2015)

Abstract

Volatiliy measurement and modeling is an important aspect in many areas of finance. The main purpose of this study is to apply seven APARCH-type models with (1,1) lags to investigate the behavior of exchange rate volatility for the EUR, JPY, and USD selling exchange rates to IDR for the duration from January 2010 to December 2015. The competing models include ARCH, GARCH, TARCH, TS-ARCH, GJR-GARCH, NARCH, and APARCH used with Gaussian normal distribution. In order to estimate the model parameters, this study applies the Bayesian inference using the adaptive random walk Metropolis method in the MCMC algorithm. Empirical results based on the deviance information criterion indicate that the GARCH (1,1), APARCH (1,1), and TARCH (1,1) models provide the best fit for the EUR, JPY, and USD data, respectively. In those models, both the JPY and USD data have significant negative leverage effect at the 99% credible level. Moreover, the JPY returns also have significant Taylor effect in return volatility at the 99% credible level.

Modeling of Returns Volatility using GARCH(1,1) Model under Tukey Transformations

“…The GARCH (1,1)-type models was applied by [20] to Indonesian commodity market, [28] to Indonesian foreign exchange market, [5] to Indonesian stock market, and [15] to Indonesian capital market. [20] examined the predictability of five GARCH-type models, namely ARCH, GARCH, GARCH-M, EGARCH, and TGARCH, for seven primary agricultural commodities in Indonesian export and found that the predictability of the considered models is different for each commodity.…”

“…[20] examined the predictability of five GARCH-type models, namely ARCH, GARCH, GARCH-M, EGARCH, and TGARCH, for seven primary agricultural commodities in Indonesian export and found that the predictability of the considered models is different for each commodity. [28] applied the GARCH (1,1) model and some of its variations, such as ARCH(1), TARCH(1,1), TS-GARCH (1,1), GJR-GARCH (1,1), NARCH(1), and APARCH(1,1), for the daily selling exchange rates of the EUR (Euro), JPY (Japanese Yen), and USD (US Dollar) against the IDR (Indonesian Rupiah) covering period from January 2010 to December 2015 and found that the GARCH (1,1) model provided the best fit for the selling rates EUR data. In that case, they used the Adaptive Random Walk Metropolis (ARWM) method in the MCMC algorithm to estimate the models.…”

Modeling of Stochastic Volatility to Validate IDR Anchor Currency

“…On the Indonesian foreign exchange market, Mukhlis (2011), Saputri et al (2016), and Salim et al (2016) investigated the behavior of exchange rate volatilities for the US dollar (USD), Japanese yen (JPY), and Euro (EUR) data sets using the GARCH-type models. Recently, Nugroho, Susanto and Pratama (2017) and investigated the daily exchange rates for the Indonesian rupiah (IDR) on return volatility using APARCH(1,1)type models. Second, our study takes two nonnested generalized Student-t distributions to the return errors' distribution and an asymmetric effect between volatility risk and asset returns in the SV model.…”

Penggunaan MS Excel untuk Estimasi Model GARCH(1,1)

“…Beberapa metode yang dapat digunakan untuk mengestimasi parameter-parameter pada model GARCH antara lain maximum likelihood (ML) method (Fan et al, [10]; Francq & Zakoian, [12]; Francq et al, [11]), least absolutely deviations estimator (Huang et al, [18]), global and local optimization methods (Adanu,[2]), dan metode Markov chain Monte Carlo (Nugroho & Susanto, [27]; Nugroho et al, [28]; Salim et al, [34]). Lebih lanjut, metode-metode estimasi tersebut dapat diimplementasikan pada perangkat lunak komputasi matematika seperti Matlab, WinBUGS, R, Stata, Phyton, SAS, dan OxMetrics.…”