Search results

The purpose of this paper is to use filtered extreme‐value theory (EVT) model to forecast one of the main emerging market stock returns and compare the predictive performance of this model with other conditional volatility models.

This paper employs eight filtered EVT models created with conditional quantile to estimate value‐at‐risk (VaR) for the Istanbul Stock Exchange. The performances of the filtered EVT models are compared to those of generalized autoregressive conditional heteroskedasticity (GARCH), GARCH with student‐t distribution, GARCH with skewed student‐t distribution, and FIGARCH by using alternative back‐testing algorithms, namely, Kupiec test, Christoffersen test, Lopez test, Diebold and Mariano test, root mean squared error (RMSE), and h‐step ahead forecasting RMSE.

The results indicate that filtered EVT performs better in terms of capturing fat‐tails in stock returns than parametric VaR models. An increase in the conditional quantile decreases h‐step ahead number of exceptions and this shows that filtered EVT with higher conditional quantile such as 40 days should be used for forward looking forecasting.

The research results show that emerging market stock return should be forecasted with filtered EVT and conditional quantile days lag length should also be estimated based on forecasting performance.

This research paper aims to discuss the effects of exchange rates on interest rates by using wavelet network methodology, which is a combination of wavelets and neural networks.

The paper employs wavelet networks to analyse the relationships between the financial time series. Empirically, the research examines the effects of foreign exchanges on the interest rates in Turkish financial markets by using daily USD/TRY rates and interest rates in Turkish Lira (TRY).

The results indicate that the wavelet network model is the most successful methodology among the alternatives such as Hodrick‐Prescott filter, feed‐forward neural network, wavelet causality, and wavelet correlation analysis in capturing the non‐linear dynamics between the selected time series.

The research results have both methodological and practical originality. On the theoretical side, the wavelet network is superior in modelling the causal linkages of the financial time series. For practical aims, on the other hand, the results show that the level of the effects of the exchange rates on the interest rates varies on the time‐scale used. Wavelet networks shows that the causality relationship is strong in the short run, while the effect decreases in the mid‐run.

This paper, using Turkish stock index data, set outs to present long‐term memory effect using chaotic and conventional unit root tests and investigate if chaotic technique as wavelets captures long‐memory better than conventional techniques.

Haar and Daubechies as wavelet‐based OLS estimator and GPH and other classical models are applied in order to investigate the performance of long memory in the time series.

The results indicate that Daubechies wavelet analysis provide the accurate determination for long memory where conventional techniques does not.

The research results have both methodological and practical originality. On the theoretical side, the wavelet‐based OLS estimator is superior in modeling the behaviours of the stock returns in emerging markets where non‐linearities and high volatility exist due to their chaotic natures. For practical aims, on the other hand, the results show that the Istanbul Stock Exchange is not in the weak‐form efficient because the prices have memories that are not reflected in the prices, yet.