Stelios D. Bekiros

Information diffusion, cluster formation and entropy-based network dynamics in equity and commodity markets

This paper investigates the dynamic causal linkages among U.S. equity and commodity futures markets via the utilization of complex network theory. We make use of rolling estimations of extended matrices and time-varying network topologies to reveal the temporal dimension of correlation and entropy relationships. A simulation analysis using randomized time series is also implemented to assess the impact of de-noising on the data dependence structure. We mainly show evidence of emphasized disparity of correlation and entropy-based centrality measurements for all markets between pre- and post-crisis periods. Our results enable the robust mapping of network influences and contagion effects while incorporating agent expectations.

Business Cycle (De)Synchronization in the Aftermath of the Global Financial Crisis: Implications for the Euro Area

Abstract The introduction of Euro currency was a game-changing event intended to induce convergence of Eurozone business cycles on the basis of greater monetary and fiscal integration. The benefit of participating into a common currency area exceeds the cost of losing autonomy in national monetary policy only in case of cycle co-movement. However, synchronization was put back mainly due to country-specific differences and asymmetries in terms of trade and fiscal policies that became profound at the outset of the global financial crisis. As opposed to previous studies that are mostly based on linear correlation or causality modeling, we utilize the cross-wavelet coherence measure to detect and identify the scale-dependent time-varying (de)synchronization effects amongst Eurozone and the broad Euro area business cycles before and after the financial crisis. Our results suggest that the enforcement of an active monetary policy by the ECB during crisis periods could provide an effective stabilization instrument for the entire Euro area. However, as dynamic patterns in the lead-lag relationships of the European economies are revealed, (de)synchronization varies across different frequency bands and time horizons.

Bayesian forecasting with small and medium scale factor-augmented vector autoregressive DSGE models

Advanced Bayesian methods are employed in estimating dynamic stochastic general equilibrium (DSGE) models. Although policymakers and practitioners are particularly interested in DSGE models, these are typically too stylized to be taken directly to the data and often yield weak prediction results. Hybrid models can deal with some of the DSGE model misspecifications. Major advances in Bayesian estimation methodology could allow these models to outperform well-known time series models and effectively deal with more complex real-world problems as richer sources of data become available. A comparative evaluation of the out-of-sample predictive performance of many different specifications of estimated DSGE models and various classes of VAR models is performed, using datasets from the US economy. Simple and hybrid DSGE models are implemented, such as DSGE-VAR and Factor Augmented DSGEs and tested against standard, Bayesian and Factor Augmented VARs. Moreover, small scale models including the real gross domestic product, the harmonized consumer price index and the nominal short-term federal funds interest rate, are comparatively assessed against medium scale models featuring additionally sticky nominal prices, wage contracts, habit formation, variable capital utilization and investment adjustment costs. The investigated period spans 1960:Q4-2010:Q4 and forecasts are produced for the out-of-sample testing period 1997:Q1-2010:Q4. This comparative validation can be useful to monetary policy analysis and macro-forecasting with the use of advanced Bayesian methods.

Evaluating direction-of-change forecasting: Neurofuzzy models vs. neural networks

This paper investigates the nonlinear predictability of technical trading rules based on a recurrent neural network as well as a neurofuzzy model. The efficiency of the trading strategies was considered upon the prediction of the direction of the market in case of NASDAQ and NIKKEI returns. The sample extends over the period 2/8/1971-4/7/1998 while the sub-period 4/8/1998-2/5/2002 has been reserved for out-of-sample testing purposes. Our results suggest that, in absence of trading costs, the return of the proposed neurofuzzy model is consistently superior to that of the recurrent neural model as well as of the buy & hold strategy for bear markets. On the other hand, we found that the buy & hold strategy produces in general higher returns than neurofuzzy models or neural networks for bull periods. The proposed neurofuzzy model which outperforms the neural network predictor allows investors to earn significantly higher returns in bear markets.

Extreme returns and the contagion effect between the foreign exchange and the stock market: evidence from Cyprus

In this article we apply the Extreme Value Theory (EVT) in order to estimate the Value-at-Risk (VaR) and the correlation of extreme returns for two inherently unstable markets; the foreign exchange and the stock market. We also derive the corresponding VaR estimates from more ‘traditional’ methods of estimation on daily returns of the US dollar/Cyprus pound exchange rate and the Cyprus stock exchange general index. The main conclusion we reach is that the more heavy-tailed distributed a series is the more accurate the loss predictions are from the application of the EVT. We also show that the conditional correlation index of the extreme returns of those two markets remained almost constant throughout the backtesting period that was characterized by ‘bear’ market conditions.

A neurofuzzy model for stock market trading

This study investigates the forecasting ability of trading strategies based on neurofuzzy models, recurrent neural networks and linear regression models. The performance of the trading strategies was considered upon the prediction of the direction-of-change of the market in case of Nikkei 255 Index returns. The results demonstrate that the profitability of the trading rule based on the neurofuzzy model is consistently higher to that of the other models as well as of a buy and hold strategy during bear market periods.

A non-linear approach for predicting stock returns and volatility with the use of investor sentiment indices

ABSTRACT The popular sentiment-based investor index SBW introduced by Baker and Wurgler (2006, 2007) is shown to have no predictive ability for stock returns. However, Huang et al. (2015) developed a new investor sentiment index, SPLS, which can predict monthly stock returns based on a linear framework. However, the linear model may lead to misspecification and lack of robustness. We provide statistical evidence that the relationship between stock returns, SBW and SPLS is characterized by structural instability and inherent nonlinearity. Given this, using a nonparametric causality approach, we show that neither SBW nor SPLS predicts stock market returns or even its volatility, as opposed to previous empirical evidence.

Macroprudential policy and forecasting using hybrid DSGE models with financial frictions and state space Markov-Switching TVP-VARs

We focus on the interaction of frictions both at the firm level and in the banking sector in order to examine the transmission mechanism of the shocks and to reflect on the response of the monetary policy to increases in interest rate spreads, using DSGE models with financial frictions. However, VAR models are linear and the solutions of DSGEs are often linear approximations; hence they do not consider time variation in parameters that could account for inherent nonlinearities and capture the adaptive underlying structure of the economy, especially in crisis periods. A novel method for time-varying VAR models is introduced. As an extension to the standard homoskedastic TVP-VAR, we employ a Markov-switching heteroskedastic error structure. Overall, we conduct a comparative empirical analysis of the out-of-sample performance of simple and hybrid DSGE models against standard VARs, BVARs, FAVARs, and TVP-VARs, using data sets from the U.S. economy. We apply advanced Bayesian and quasi-optimal filtering techniques in estimating and forecasting the models.

Evolutionary-based return forecasting with nonlinear STAR models: evidence from the Eurozone peripheral stock markets

Traditional linear regression and time-series models often fail to produce accurate forecasts due to inherent nonlinearities and structural instabilities, which characterize financial markets and challenge the Efficient Market Hypothesis. Machine learning techniques are becoming widespread tools for return forecasting as they are capable of dealing efficiently with nonlinear modeling. An evolutionary programming approach based on genetic algorithms is introduced in order to estimate and fine-tune the parameters of the STAR-class models, as opposed to conventional techniques. Using a hybrid method we employ trading rules that generate excess returns for the Eurozone southern periphery stock markets, over a long out-of-sample period after the introduction of the Euro common currency. Our results may have important implications for market efficiency and predictability. Investment or trading strategies based on the proposed approach may allow market agents to earn higher returns.

Money supply and inflation dynamics in the Asia-Pacific economies: a time-frequency approach

Abstract: We examine the relationship between money supply growth and inflation in 3 Asian Economies which are India, Malaysia and Japan using a time-frequency approach. The application of a unified multi-scale analysis allows us to provide a continuous assessment of the link between money supply growth and inflation, unlike most of the existing literature studying this relationship. We also employ a bivariate frequency-domain causality test to determine the nature and direction of interdependence between money supply growth and inflation dynamics. Our findings provide a better understanding of their lead-lag linkages and causal relationship in the selected countries of the Asia-Pacific region.