Dr. Mohd Tahir Ismail

University: Universiti Sains Malaysia
Department: School of Mathematical Sciences
Research Fields: Financial Time Series

Publications

3 A Comparative Study between Discrete Wavelet Transform and Maximal Overlap Discrete Wavelet Transform for Testing Stationarity

Authors: Mohd Tahir Ismail, Amel Abdoullah Ahmed Dghais

Abstract:

In this paper the core objective is to apply discrete wavelet transform and maximal overlap discrete wavelet transform functions namely Haar, Daubechies2, Symmlet4, Coiflet2 and discrete approximation of the Meyer wavelets in non stationary financial time series data from Dow Jones index (DJIA30) of US stock market. The data consists of 2048 daily data of closing index from December 17, 2004 to October 23, 2012. Unit root test affirms that the data is non stationary in the level. A comparison between the results to transform non stationary data to stationary data using aforesaid transforms is given which clearly shows that the decomposition stock market index by discrete wavelet transform is better than maximal overlap discrete wavelet transform for original data.

Keywords: discrete wavelet transform, stationarity, maximal overlap discrete wavelet transform, autocorrelation function

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4320
2 Designing Early Warning System: Prediction Accuracy of Currency Crisis by Using k-Nearest Neighbour Method

Authors: Mohd Tahir Ismail, Nor Azuana Ramli, Hooy Chee Wooi

Abstract:

Developing a stable early warning system (EWS) model that is capable to give an accurate prediction is a challenging task. This paper introduces k-nearest neighbour (k-NN) method which never been applied in predicting currency crisis before with the aim of increasing the prediction accuracy. The proposed k-NN performance depends on the choice of a distance that is used where in our analysis; we take the Euclidean distance and the Manhattan as a consideration. For the comparison, we employ three other methods which are logistic regression analysis (logit), back-propagation neural network (NN) and sequential minimal optimization (SMO). The analysis using datasets from 8 countries and 13 macro-economic indicators for each country shows that the proposed k-NN method with k = 4 and Manhattan distance performs better than the other methods.

Keywords: Neural Network, Currency Crisis, logit, k-nearest neighbour method

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1930
1 Statistical Computational of Volatility in Financial Time Series Data

Authors: Mohd Tahir Ismail, S. Al Wadi, Samsul Ariffin Abdul Karim

Abstract:

It is well known that during the developments in the economic sector and through the financial crises occur everywhere in the whole world, volatility measurement is the most important concept in financial time series. Therefore in this paper we discuss the volatility for Amman stocks market (Jordan) for certain period of time. Since wavelet transform is one of the most famous filtering methods and grows up very quickly in the last decade, we compare this method with the traditional technique, Fast Fourier transform to decide the best method for analyzing the volatility. The comparison will be done on some of the statistical properties by using Matlab program.

Keywords: Fast Fourier Transforms, volatility, Haar wavelet transform, Matlab (Wavelet tools), stocks market

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1943

Abstracts

1 Hybrid Robust Estimation via Median Filter and Wavelet Thresholding with Automatic Boundary Correction

Authors: Mohd Tahir Ismail, Alsaidi M. Altaher

Abstract:

Wavelet thresholding has been a power tool in curve estimation and data analysis. In the presence of outliers this non parametric estimator can not suppress the outliers involved. This study proposes a new two-stage combined method based on the use of the median filter as primary step before applying wavelet thresholding. After suppressing the outliers in a signal through the median filter, the classical wavelet thresholding is then applied for removing the remaining noise. We use automatic boundary corrections; using a low order polynomial model or local polynomial model as a more realistic rule to correct the bias at the boundary region; instead of using the classical assumptions such periodic or symmetric. A simulation experiment has been conducted to evaluate the numerical performance of the proposed method. Results show strong evidences that the proposed method is extremely effective in terms of correcting the boundary bias and eliminating outlier’s sensitivity.

Keywords: Simulation, boundary correction, median filter, wavelet thresholding

Procedia PDF Downloads 290