Communications in Computational and Applied Mathematics

Regression Analysis to Rank: Evidence from Profit Risk and Efficiency

2020-10-22T03:45:31+08:00

This investigation assesses the connection between specialized efficiency and profit risk of the money related organizations recorded in Bursa Malaysia by using market information over the time period 2007-2016. Besides, this investigation likewise focuses on the positioning of the organizations as per productivity scores. DEA is used on a MPI to ascertain the money related organizations' effectiveness scores. The consequences of this examination show that APEX, JOHAN, ECM, MAA, AEONCR, and LPI were completely effective organizations that imply these organizations were in ideal control of their data sources or assets to create the greatest outputs. The least effective organization was MAYBANK. Also, the outcomes found that benefit chance positively affected proficiency that communicates support of positioning of the organizations. This examination is noteworthy in light of the fact that it will assist investors in identifying the less risk efficient organization from the money related organizations of Bursa Malaysia.

Robust Multivariate Exponential Weighted Moving Average Control Chart for Monitoring Multivariate Contaminated Data

2020-10-22T03:45:31+08:00

Multivariate exponential weighted moving average (MEWMA) control chart is one of the multivariate control charts used for observing the stability of non-random pattern in a process. However, high dimension multivariate time series data have high possibility of outliers, in the dataset. The effect of outliers may jeopardize the performance of Phase II MEWMA control chart. In this paper, we have shown that the performance of the existing MEWMA control chart is not robust across contaminated data, even for the smallest percentage of outliers, producing high empirical false alarm rates. To alleviate the problem, robust control chart based on location and scale estimators of Winsorized MOM was proposed. The results shown the proposed robust control chart is more efficient in controlling the empirical false alarm rates close to the false alarm rate value compared to the existing MEWMA control chart.

The Effect of Uncertainty Avoidance on Job Performance of Government Employees in Pahang Darul Makmur: A Regression Analysis Approach

2020-10-22T03:45:31+08:00

Research has shown that culture has an impact on how business activities are conducted in an organization. Thus, it affects the performance of the organization as a whole. The study focused specifically on Hofstede’s cultural dimension of uncertainty avoidance in relation to job performance of government employees in Pahang Darul Makmur. Uncertainty avoidance is described as the degree to which a person in a society accommodates uncertainty and ambiguity in the environment. The regression analysis approach using IBM-SPSS AMOS 24 software was used to determine the effect of uncertainty avoidance on job performance. A total of 176 respondents were conveniently selected to participate in this study and answered a set of questionnaire. This study found that moderate positive relationship (r = .513, p = .000) existed between the two variables. In addition, there exists positive significance effect of uncertainty avoidance on job performance, whereby the uncertainty avoidance was identified as significant predictor (β = 0.453, p = .000). The result indicated that the greater the uncertainty avoidance culture, the employees tends to have positive motivation towards their job performance. The study concluded that majority of the government employees still depends heavily upon instructions and regulations set by the organization in the course of completing their tasks. They are not risk takers thus prefer greater structure in every situation and follow the norms of the society.

Optical Soliton Simulation by Pseudospectral Method

2020-10-22T03:45:31+08:00

The dispersive phenomenon of group velocity dispersion (GVD) and fiber nonlinearity of self-phase modulation restrict the performance of the optical fiber communication, however, when there is an equilibrium between dispersive and nonlinearity effects, a solitary wave or soliton is generated. The soliton can propagate for a long-distance undistorted. This property makes it suitable to be employed in ultra-long haul communication. Optical soliton propagation in optical fiber is described by the nonlinear Schrodinger (NLS) equation. This research simulated optical soliton propagation by solving the NLS equation employing the pseudospectral method. It shows the optical soliton preserves its shape and amplitude for 100 km simulation.

Improved Circular Model on Forecasting Arrivals from Western European Countries to Sri Lanka

2020-10-22T03:45:31+08:00

The Circular Model (CM) is a newly joined member to the family of Univariate Statistical Models. Development of the CM was based on; Newton’s Law of Circular Motion, Fourier Transformation and Least Square Regression. The CM could be applied for either stationary or non-stationary series and is capable of capturing both seasonal and cyclical variations. However, the applicability of CM is restricted to trend free series, hence it was intended to overcome the limitation. The Improved Circular Model; named as, Sama Circular Model (SCM), tests on tourist arrival data from Western European countries to Sri Lanka. Forecasting ability of the SCM was compared with the Decomposition techniques and Seasonal Auto Regressive Integrated Moving Average. It is concluded that the SCM is capable in forecasting arrivals from Western European countries and superior to the other tested models.

Computation of Multidimensional Conditional Distribution Function

2020-10-22T03:45:31+08:00

An important method of forming univariate time series models is by means of conditional distributions. For a vector having a power-normal distribution of dimension k, it is already possible to find approximately the conditional distribution of the last element in the vector. This paper extends the previous result on univariate conditional distribution to conditional distribution in the light of the values of the initial k-m elements in the vector. The extended results can be used to form multivariate time series models. The new numerical procedure offers an easy way to obtain satisfactory results.