Adnen Ben Nasr

Modelling the volatility of the Dow Jones Islamic Market World Index using a fractionally integrated time-varying GARCH (FITVGARCH) model

Appropriate modelling of the process of volatility has implications for portfolio selection, the pricing of derivative securities and risk management. Further, a large body of research has suggested that both long memory and structural changes simultaneously characterize the structure of financial returns volatility. Given this, in this article, we aim to model conditional volatility of the returns of the Dow Jones Islamic Market World Index (DJIM), interest on which has come to the fore following the need for renovation of the conventional financial system, in the wake of the recent global financial crisis. To model the conditional volatility of the DJIM returns, accounting for both long memory and structural changes, we allow the parameters in the conditional variance equation of the fractionally integrated generalized autoregressive conditional heteroscedasticity (FIGARCH) model to be time dependent, such that the parameters evolve smoothly over time based on a logistic smooth transition function, yielding a fractionally integrated time-varying generalized autoregressive conditional heteroscedasticity (FITVGARCH) model. Our results show that, in terms of model diagnostics and information criteria, as well as, portfolio allocation, the FITVGARCH model performs better than the FIGARCH model in explaining conditional volatility of the DJIM returns, thus, highlighting the need to model simultaneously long memory and structural changes in the volatility process of asset returns.

Fractionally integrated time varying GARCH model

This paper introduces the new FITVGARCH model to describe both long memory and structural change behaviour in the volatility process by allowing for time varying dynamic structure in the conditional variance. The parameters of the conditional variance in the FIGARCH model are allowed to change smoothly over time. We derive an LM-type test for parameter constancy of the FIGARCH model against the alternative of time dependent parameters. Simulation analysis shows that both empirical size and power of the constancy test are quite good. An empirical application to the stock market volatility indicates that this new class of model seems to outperform the FIGARCH model in the description of the daily NASDAQ composite index returns.

Seasonal and Periodic Long Memory Models in the Inflation Rates

This paper considers the application of long memory processes to describe inflation with seasonal behaviour. We use three different long memory models taking into account the seasonal pattern in the data. Namely, the ARFIMA model with deterministic seasonality, the ARFISMA model, and the periodic ARFIMA (PARFIMA) model. These models are used to describe the inflation rates of four different countries, USA, Canada, Tunisia, and South Africa. The analysis is carried out using the Sowells (1992) maximum likelihood techniques for estimating ARFIMA model and using the approximate maximum likelihood method for the estimation of the PARFIMA process. We implement a new procedure to obtain the maximum likelihood estimates of the ARFISMA model, in which dummies variables on additive outliers are included. The advantage of this parametric estimation method is that all parameters are estimated simultaneously in the time domain. For all countries, we find that estimates of differencing parameters are significantly different from zero. This is evidence in favour of long memory and suggests that persistence is a common feature for inflation series. Note that neglecting the existence of additive outliers may possibly biased estimates of the seasonal and periodic long memory models.

A Nonlinear Approach for Modeling and Forecasting US Business Cycles

Abstract The purpose of this paper is to provide a complete evaluation of four regime-switching models by checking their performance in detecting US business cycle turning points, in replicating US business cycle features and in forecasting US GDP growth rate. Both individual and combined forecasts are considered. Results indicate that while the Markov-switching model succeeded in replicating all the NBER peak and trough dates without an extra-cycle detection, it seems to be outperformed by the Bounce-back model in term of the delay time to a correct alarm. Concerning business cycle features characterization, none of the competing models dominates over all the features. The performance of the Markov-switching and bounce back models in detecting turning points was not translated into an improved business cycle feature characterization since they are outperformed by the Floor and Ceiling model. The forecast performance of the considered models varies across regimes and across forecast horizons. That is, the model performing best in an expansion period is not necessarily the same in a recession period and similarly for the forecast horizons. Finally, combining such individual forecasts generally leads to increased forecast accuracy especially for h=1.