Estimating stock market volatility using asymmetric GARCH models

Abstract

A comprehensive empirical analysis of the mean return and conditional variance of Tel Aviv Stock Exchange (TASE) indices is performed using various GARCH models. The prediction performance of these conditional changing variance models is compared to newer asymmetric GJR and APARCH models. We also quantify the day-of-the-week effect and the leverage effect and test for asymmetric volatility. Our results show that the asymmetric GARCH model with fat-tailed densities improves overall estimation for measuring conditional variance. The EGARCH model using a skewed Student-t distribution is the most successful for forecasting TASE indices.

Asymmetric GARCH and the Financial Crisis: A Preliminary Study

“…The Asymmetric Power ARCH (APARCH henceforth) model by DingGranger -Engle (1993) is probably one of the most interesting ARCH type models 1 . It can be expressed as:…”

“…As the estimated coefficients 1  and 1  shown in the Table 2 are both negative, The next step in our analysis was the calculation of NIC for models from the crisis dataset. As in the case of GARCH and TGARCH models we have used ARCH order of 2, the news impact curve changes to news impact surface.…”

A Generalized Asymmetric Student-t Distribution with Application to Financial Econometrics

“…where K(·) and B are defined respectively in (1) and (3). We see that all the moments can be expressed simply and conveniently in terms of the Gamma function.…”

“…For example, Bollerslev (1987) used the Student-t to model the distribution of foreign exchange rate returns; Mittnik, Rachev and Paolella (1998) fitted a return distribution using a number of parametric distributions including Student-t, and found that the partially asymmetric Weibull, Student-t and the asymmetric stable distributions provide the best fit according to various measures. Recent applications include Alberg et al (2008) and Franses et al (2008). Hansen (1994) was the first to consider a skewed Student's t distribution to model skewness in conditional distributions of financial returns.…”

Impact of Political News: Evidence from Russia

“…Moreover, it helps to obtain more robust estimates because EGARCH and APARCH models' structure has some differences (Karanasos and Kim, 2003). Particularly, such a method was used for model testing on Thai (Kongprajya, 2010) and Israeli stock markets (Alberg et al, 2008). In addition, this model enables to check some other parameters of EGARCH and GARCH models, such as: effect of stability of shocks' impact on volatility and presence of risk premium.…”