Advances and Applications in Statistics
Volume 53, Issue 4, Pages 325 - 343
(October 2018) http://dx.doi.org/10.17654/AS053040325 |
|
MODELLING EGX30 OF EGYPTIAN STOCK MARKET USING SPECTRAL ANALYSIS AND HARMONIC REGRESSION
Essam Fawzy Aziz
|
Abstract: The Egyptian stock market is one of the important means in the financial sector, which works to achieve a return of funds invested in the form of stocks and bonds. The stock market attracts various savings from individuals and economic institutions. Investors carry a single financial paper. They usually carry a portfolio of securities called the investment portfolio, so the investor chooses the efficient portfolio that achieves the highest expected return at a certain level of risk. The objective of this research is to propose a statistical model to predict EGX30 index. This article covered daily time series of the most important factor (EGX30) from 3/11/2014 until 23/5/2018. Diagnostic analysis showed that the time series data has no outlier and the data are normally distributed. Spectral analysis produced the wavelength of 5, 10, 15 and 20 describing the seasonality of the time series. Harmonic regression model fits the data well with transformation of square root of the original values. Coefficient of determination was 0.689 explaining the changes of EGX30 can refer to a sequence of the times. |
Keywords and phrases: spectral analysis, harmonic regression, outlier identification, periodogram, wavelength.
|
|
Number of Downloads: 462 | Number of Views: 3482 |
|