Berna Yazici

A comparison of various tests of normality

This article studies twelve different normality tests that are used for assessing the assumption that a sample was drawn from a normally distributed population and compares their powers. The tests in question are chi-square, Kolmogorov–Smirnov, Anderson–Darling, Kuiper, Shapiro–Wilk, Ajne, modified Ajne, modified Kuiper, D’Agostino, modified Kolmogorov–Smirnov, Vasicek, and Jarque–Bera. Each test is described and power comparisons are also obtained by using Monte Carlo computations. To do this, first, normally distributed populations with different standard deviations are taken and then simulation is conducted for nonnormal populations. The results are discussed and interpreted separately.

Comparison of ARIMA, neural networks and hybrid models in time series: tourist arrival forecasting

For time series forecasting, different artificial neural network (ANN) and hybrid models are recommended as alternatives to commonly used autoregressive integrated moving average (ARIMA) models. Recently, combined models with both linear and nonlinear models have greater attention. In this article, ARIMA, linear ANN, multilayer perceptron (MLP), and radial basis function network (RBFN) models are considered along with various combinations of these models for forecasting tourist arrivals to Turkey. Comparison of forecasting performances shows that models with nonlinear components give a better performance.

Assessment of the levels of heavy metal pollution in roadside soils of Eskisehir, Turkey

A detailed study was conducted to determine the current status of the heavy metals Cd, Cu, Cr, Fe, Hg, Mn, Ni, Pb, and Zn in Eskisehir, Turkey. The 15 different locations (n =270) studied were specifically selected to identify the effects of soil pollution on the tramway, which has been in service since December 2004 for public transportation in Eskisehir. The samples were taken from three different lines: tramway-only lines, traffic-only lines, and both traffic and tramway lines. The pollution level was estimated based on the geoaccumulation index (I(geo)), the enrichment factor (EF), the pollution index, and the integrated pollution index (IPI). The values for the IPI were in the following order: Pb > Zn > Cu > Fe > Mn > Ni > Cr > Cd, but mercury was not detected at any sample point. These indexes for metals in the soils under consideration correlated with either low or median levels of pollution. In addition, descriptive statistics were provided for the heavy metals under consideration, and box-plots were constructed and interpreted for all measured indices.

Robust ridge and robust Liu estimator for regression based on the LTS estimator

In the multiple linear regression analysis, the ridge regression estimator and the Liu estimator are often used to address multicollinearity. Besides multicollinearity, outliers are also a problem in the multiple linear regression analysis. We propose new biased estimators based on the least trimmed squares (LTS) ridge estimator and the LTS Liu estimator in the case of the presence of both outliers and multicollinearity. For this purpose, a simulation study is conducted in order to see the difference between the robust ridge estimator and the robust Liu estimator in terms of their effectiveness; the mean square error. In our simulations, the behavior of the new biased estimators is examined for types of outliers: X-space outlier, Y-space outlier, and X-and Y-space outlier. The results for a number of different illustrative cases are presented. This paper also provides the results for the robust ridge regression and robust Liu estimators based on a real-life data set combining the problem of multicollinearity and outliers.

Measurement of internal user satisfaction and acceptance of the e-justice system in Turkey

Purpose The purpose of this paper is to develop an evaluation model for National Judiciary Informatics System (NJIS), which is an e-justice system forming part of e-government, based on the models and the theories of information systems (ISs). Design/methodology/approach The survey was conducted on 8,840 internal users working for judicial services in Turkey. The success of the NJIS as an e-justice system is evaluated using structural equation modeling (SEM). Findings The results show that while the most important factor is the latent variable information quality in the SEM created to analyze the satisfaction of internal users using the NJIS, other factors include perceived usefulness (PU), system quality, and service quality, respectively. It is found that design quality has affected directly and positively the perceived ease of use (PEoU) while PEoU has affected the PU in the same manner. Research limitations/implications This study was solely concerned with internal users. Therefore, a more comparative study in which other users such as lawyers and ordinary citizens can be incorporated is suggested. Related to internal user satisfaction of the e-justice system, it is explored whether or not internal users are satisfied with their information processing needs, the system’s efficiency, the number of process steps, technical office services, and the system in general. Originality/value The research presents a new developed evaluation model of e-justice system from an internal user perspective. Most evaluation models focus on system-centered evaluation or organizational structure while user-centered evaluation concerning judicial ISs has not been explored yet.

Determining the problems of disabled employees: a survey study conducted in Eskişehir, Turkey

In this study, disabled people, employed using a policy based quota method, were asked about their working lives by means of a survey. In order to do this, the population was defined as disabled people working for companies which are obliged by law to employ disabled people, as well as the employees and the employers of these companies in Eskişehir, Turkey. According to the quota method approximately 1000 disabled people are employed in Eskişehir. Two different questionnaires were issued: one covered 421 disabled employees and the other their 31 employers working for 32 different companies both from the private and the public sectors in Eskişehir, Turkey. The data obtained from the research has been statistically analyzed and the results are interpreted. The conclusion is that improvements should be carried out in order to make disabled employees’ lives easier in Turkey.

Analysis of international debt problem using artificial neural networks and statistical methods

It is known from the scientific researches that artificial neural networks are alternatives of statistical methods such as regression analysis and classification in recent years. Since multi-layer backpropagation neural network models are nonlinear, it is expected that the neural network models should make better classifications and predictions. The studies on this subject support that idea. In this study, a macro-economic problem on rescheduling or non-rescheduling of the countries’ international debts is taken into account. Among the statistical methods, logistic and probit regression, and the different neural network backpropagation algorithms are applied and comparisons are made. Evaluations and suggestions are made depending on the results and different neural network architecture.

Comparison of confidence intervals for the Behrens-Fisher problem

ABSTRACT The Behrens–Fisher problem concerns the inferences for the difference between means of two independent normal populations without the assumption of equality of variances. In this article, we compare three approximate confidence intervals and a generalized confidence interval for the Behrens–Fisher problem. We also show how to obtain simultaneous confidence intervals for the three population case (analysis of variance, ANOVA) by the Bonferroni correction factor. We conduct an extensive simulation study to evaluate these methods in respect to their type I error rate, power, expected confidence interval width, and coverage probability. Finally, the considered methods are applied to two real dataset.

A Simulation Study on Generalized Pareto Mixture Model

The Generalized Pareto Distribution is commonly used for extreme value problems. Especially, the values which exceed the finite threshold, is the focus in extreme value problems like in insurance sector. The Generalized Pareto Distribution is well approach for modeling the samples which include these extreme values. In the real life, samples are heterogeneous. In such cases, the mixture models are better way for modeling the data. In this study, we generate random samples from the Generalized Pareto Mixture Distribution for modeling of heterogeneous data. For this purpose, we use two different Generalized Pareto Distribution as components of the Generalized Pareto Mixture Distribution. For generating random samples, The Inverse Transformation Method is used in the simulation study. The parameters of the mixture models are shape, scale and location are fixed. After generating random samples, Chi-Square Goodness-of-Fit Test is used for checking whether the generated samples are distributed based on the Generalized Pareto Distribution. R-Statistical Programming Language is used in simulation study.

Trust in adoption to judiciary informatics system of senior management users

With the start of performing judiciary informatics in Turkey through information systems, especially the adoption of internal users carrying out these activities started to be significant. Senior management users (Chief Judges, Judges, Attorneys General and Solicitors) form an outstanding user groups which will contribute to solving possible problems in information systems. In this study, besides trust variable which has an effective role in senior management users adoption of information systems, occupation, age and gender variables are analysed. Web based questionnaire, which is prepared as five point Likert type scale including 593 senior management users, is analysed and interpreted through log linear method.