Shamshuritawati Sharif

Foreign currency exchange network topology across the 2008 credit crisis

A stable world currency exchange rate is a very important aspect to be considered for a developed country, i.e Malaysia. A better understanding about the currencies itself is needed nowadays. This project is about to understanding the fluctuation and to identify the most influential world currencies in the three different cases; before credit crisis, during credit crisis and after credit crisis. A network topology approach is use to examine the interrelationship between currencies based on correlation analysis. With this point of view, those relationships can be measured by a correlation structure among the currencies. The network can be analyse by filtering the important information using minimum spanning tree (MST) and interpret it using degree centrality as the centrality measure. This topology will give a useful guide to understand the behaviour and determine the most influential currency in the network as a part of a complex system. All currencies are compared among the three different cases; before ...

Asymptotic derivation of T* statistic

Monitoring the stability of correlation structure becomes an imperative subject in economic development and financial industry. It has been extensively implemented by various researchers to understand the behaviour of a sequence of correlation structures based on independent samples in certain time periods. The existing statistical test can only tackle problems involving p n due to the inversion of covariance matrix. Therefore, in this paper we introduced T* statistics, constructed based on upper-off-diagonal elements to overwhelm that difficulty. The limitation distribution has been investigated to make its application promising.

An application of network topology to understand the signal in process variability: A case study in petrochemical industry

This paper deals with a network topology approach for identifying the root causes of an out-of-control signal. An experience in the production process of fertilizer will be reported.

The impact of 2008 credit crisis on currency stability structure

The depreciation of many currencies over the world has retarded the economic development during 2008 credit crisis. The aim of this study is to detect the existence of changes in the currency stability structure by using a new covariance structure test known as S* statistics for high dimensional data involving 74 currencies. Comparisons were made between monthly data and overall data of 2008. Further analysis was conducted using network topology to visualise the pattern of structural changes and identifying which currencies affected by the crisis. The findings disclose that October currency structure has the utmost changes as compared to overall structure 2008. Forty one (or 55%) currencies were affected. The most affected currencies were Austrian schilling (ATS) and followed by Lebanese pound (LBP) and Mexican peso (MXN). These findings reflect the major impact of 2008 credit crisis on deterioration currencies performance.

Identifying influential variables in complex system: Network topology versus principal component analysis

High dimensional covariance structure can be considered as a complex system that relates each variable to the others in terms of variability. In complex system, identifying influential variables is a very important part of reliability analysis, which has been a key issue in analysing the structural organization of a system. To analyse such complex system, network topology and principal component analysis are constructed to simplify the system. Network topology can be used to simplify the information about the system and centrality measure will be used to interpret the network. In the other hand, the principal component analysis can be used to eliminate the variables that contribute little extra information. An example will be discussed to illustrate the advantage and disadvantage of network topology and principal component analysis and a recommendation will be presented.

Understanding the Shift of Correlation Matrices During Financial Crisis: A Network Topology

Understanding the shift of correlation matrices in any process is not an easy task. From the literatures, the most popular and widely used test for correlation shift is Jennrichs test. This motivates us to use it in this paper. However, if after hypothesis testing the hypothesis of stable process correlation is rejected, then the next problem is to find out the root causes of that situation. In this paper, network topology approach will be used to understand the shift. A case study will be discussed and presented to illustrate the advantage of this approach.

Worker’s behaviour in manufacturing industry: An evidence from a minimum spanning tree

A manufacturing industry contributes around 10% Malaysian economic. It provides economic opportunities for related industries and business. However, the number of accidents in manufacturing sector, including fatal accidents, has been increased from time to time. We analyze worker’s behaviour to understand the real situation. The method developed in econophysics has been used to transform the correlation structure into sub-dominant ultrametric structure. Its corresponding minimum spanning tree and the centrality measure are performed in order to identify the most influential variables.

Improved closeness centrality using arithmetic mean approach

In this paper, we improved the mathematical formulation of closeness centrality measure for weighted network. The proposed measure is used arithmetic mean approach and the performance is successfully better than the existing closeness centrality. This measure can be used as a measure of influential nodes.

Computational efficiency of generalized variance and vector variance

In multivariate statistical quality control, the existing tests known as Generalized Variance (GV) and Vector Variance (VV), plays an important role in measuring process variability. In this paper, we present the computational efficiency of both tests to illustrate that their complexity as a function of dimension. From the mathematical derivation and simulation study, the computational efficiency of VV outperforms GV, particularly when the number of variables is large.

A gap analysis to identify the outlier of stocks traded at Bursa Malaysia

In stock networks analysis, the influential stocks is usually identified by using minimal spanning tree (MST) to filter the important information followed by the centrality measures analysis. In this paper, we introduce an analysis to identify the stocks that might have different behaviour compared to the others. Like the centrality measures analysis, this analysis is also conducted based on MST. A case study on stock networks at KLSE will be reported and discussed.