Publisher: U of the Punjab (Total: 5 journals) [Sort by number of followers]

Similar Journals
Pakistan Journal of Statistics and Operation Research
Journal Prestige (SJR): 0.383 Citation Impact (citeScore): 1 Number of Followers: 1 Open Access journal ISSN (Print) 18162711  ISSN (Online) 22205810 Published by U of the Punjab [5 journals] 
 Paradox in The dDimensional Fixed Charge Transportation Problem and
Algorithm for Finding The Paradox
Authors: Bib Paruhum Silalahi, Eko Sulistyono, Fahren Bukhari
Pages: 329  336
Abstract: The ddimensional fixed charge transportation problem is a generalization of fixed charge transportation. This problem has dtype of constraints so that can be applied to more complex problem. In transportation problem, sometimes there is a cases when increase the product in shipping, the number of costs incurred is less than before the increase of product. This problem is called the transportation paradox. In this research, it will be explained about the model of ddimensional fixed charge transportation problem and sufficient condition for the occurrence of the paradox. Furthermore an algorithm is given in finding the paradox in the ddimensional fixed charge transportation problem with example to support the theory presented.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.2807
 Huber Mestimator for Cumulative Odds Model with Application to the
Measurement of Students' Final Exam Grades
Authors: Faiz Bin Zulkifli, Zulkifley Bin Mohmed, Nor Afzalina Binti Azmee
Pages: 337  347
Abstract: The Huber Mestimator is proposed in this study as a robust method for estimating the parameters of the cumulative odds model, which includes a logistic link function and polytomous explanatory variables. With the help of an intensive Monte Carlo simulation study carried out using the statistical software R, this study evaluates the performance of the maximum likelihood estimator (MLE) and the robust technique developed. Bias, RMSE, and the Lipsitz Statistic are used to measure comparisons. When conducting the simulation study, different sample sizes, contamination proportions, and error standard deviations are considered. Preliminary findings indicate that the Mestimator with Huber weight estimates produces the best results for parameter estimation and overall model fitting compared to the MLE. As an illustration, the procedure is applied to realworld data of students' final exam grades as measured by two different estimators.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.2996
 The Exponentiated Generalized Alpha Power Family of Distribution:
Properties and Applications
Authors: ElSayed A. ElSherpieny, Ehab Mohamed Almetwally
Pages: 349  367
Abstract: In this paper, we introduce the exponentiated generalized alpha power family of distributions to extend the several other distributions. We used the new family to discuss the exponentiated generalized alpha power exponential (EGAPEx) distribution. Some statistical properties of the EGAPEx distribution are obtained. The model parameters are obtained by the maximum likelihood estimation (MLE), maximum product spacing (MPS) and Bayesian estimation methods. A Monte Carlo Simulation is performed to compare between different methods. We illustrate the performance of the proposed new family of distributions by means of two real data sets and the data sets show the new family of distributions is more appropriate as compared to the exponentiated generalized exponential, alpha power generalized exponential, alpha power exponential, generalized exponential and exponential distributions.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.3515
 A New Transmuted Weibull Distribution: Properties and Application
Authors: Aliya Syed Malik, S.P. Ahmad
Pages: 369  381
Abstract: This paper proposes a new three parameter Weibull distribution obtained using a new Transmutation technique namely New Transmuted Weibull distribution. A comprehensive account of some of the mathematical properties of new model are derived. Entropy estimation and parameter estimation is also carried out using different methods. Finally, it will be shown that the analytical results are applicable to model real data.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.2728
 The Effect Of International Aid On Per Capita Income: A Panel Data
Analysis
Authors: Fatma Feyza GÜNDÜZ, Özlem AKAY
Pages: 383  394
Abstract: Poverty, a problem that has existed throughout the history of humanity and sought a solution, is a phenomenon that is struggled under the joint responsibility of world states, national and international organizations. As a result of the positive and economic developments after the World War II, with the implementation of social spending programs, a transition to a systematic structure has been achieved in the struggle against poverty. In this study, a panel data set covering the period 20042018 for 23 countries was constructed to examine the impact of international aid on per capita income. The study results show a positive relationship between the international aid, population, and human development index and per capita gross domestic product at the 5% significance level, a negative relationship between the unemployment rate and the Gini coefficient and per capita income at the 5% significance level. If the international aid increases by 1%, the per capita income increases by 0.08%, if the population increases by 1%, the per capita income increases by 1.45%, if the value of human development increases by 1%, the per capita income increases by 1.60%. If the unemployment rate increases by 1%, per capita income decreases by 0.15%; if the Gini coefficient increases by 1%, the per capita income decreases by 0.63%.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.4042
 The Infinite Divisibility of Compound Negative Binomial Distribution as
the Sum of Laplace Distribution
Authors: Dodi Devianto, Stefi Amalia Fitri, Hazmira Yoza, Maiyastri Maiyastri
Pages: 395  402
Abstract: The infinite divisibility of compound negative binomial distribution especially as the sum of Laplace distribution has important roles in governing the mathematical model based on its characteristic function. In order to show the property of characteristic function of this compound negative binomial distribution, it is used FourierStieltjes transform to have characteristic function and then governed the property of continuity and quadratic form by using analytical approaches. The infinite divisibility property is obtained by introducing a function satisfied the criteria to be a characteristic function such that its convolution has the characteristic function of compound negative binomial distribution. Then it is concluded that the characteristic function of compound negative binomial distribution as the sum of Laplace distribution satisfies the property of continuity, quadratic form and infinite divisibility.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.2767
 New Exponential Ratio Estimator in Ranked Set Sampling
Authors: Rather Khalid, Eda Gizem KOÇYİĞİT, Ceren ÜNAL
Pages: 403  409
Abstract: In this study, we adapted the families of estimators from Ünal and Kadilar (2021) using the exponential function for the population mean in case of nonresponse for simple random sampling for the estimation of the mean of the population with the RSS (ranked set sampling) method. The equations for the MSE and the bias of the adapted estimators are obtained for RSS and it in theory shows that the proposed estimator is additional efficient than the present RSS mean estimators in the literature. In addition, we support these theoretical results with real COVID19 real data and conjointly the simulation studies with different distributions and parameters. As a result of the study, it was observed that the efficiency of the proposed estimator was better than the other estimators.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.3921
 Decomposition Method with Application of Grey Model GM(1,1) for
Forecasting Seasonal Time Series
Authors: Mujiati Dwi Kartikasari, Nur Hikmah
Pages: 411  416
Abstract: Forecasting is one of the activities needed by companies to determine the policies that need to be taken for the continuity of operations. There are many methods for forecasting, one of which is the grey model GM(1,1). The GM(1,1) is one of the successful forecasting methods applied to economics, finance, engineering, and others. However, according to several previous study, the GM(1,1) is not good enough to forecast data containing seasonal characteristics. Therefore, the aim of this study is to develop hybrid model so that the GM(1,1) is able to forecast seasonal time series. The hybrid model is constructed by combining decomposition method for seasonality adjustment and grey model GM(1,1) for forecasting seasonal time series. The results are compared to seasonal grey model SGM(1,1). Based on the evaluation using error criteria, it is found that the hybrid model is the best model.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.3533
 Mathematical Modeling of AgeSpecific Fertility Rates of Nepali Mothers
Authors: Arjun Kumar Gaire, Gyan Bahadur Thapa, Samir K. C.
Pages: 417  426
Abstract: In this paper, polynomial models have been formulated to describe the distribution pattern of agespecific fertility rates (ASFRs) and forwardcumulative ASFRs of Nepali mothers. The former follows the biquadratic polynomial and the latter follows the quadratic one. Velocity and elasticity equations of the fitted models have been formulated. The areas covered by the curves of the fitted models have been evaluated, and the area covered by the curve of ASFRs is equivalent to the total fertility rate (TFR). Furthermore, the mode of the fitted ASFRs has been estimated. To test the stability and validity of fitted models, cross validity prediction power, shrinkage of the model, Ftest statistics and the coefficient of determination have been applied.
PubDate: 20220601
DOI: 10.18187/pjsor.v18i2.3319
 The Support Vector Regression Model: A new Improvement for some Data
Reduction Methods with Application
Authors: Moustafa Salem, Mohamed G. Khalil
Pages: 427  435
Abstract: Support Vector Regression (SVR) formulates is an optimization problem to learn a regression function that maps from input predictor variables to output observed response values. The SVR is useful because it balances model complexity and prediction error, and it has good performance for handling highdimensional data. In this paper, we use the SVR model to improve the principal component analysis and the factor analysis methods. Simulation experiments are performed to assessment the new method. Some useful applications to real data sets are presented for comparing the competitive SVR models. It is noted that with increasing sample size, the SVR type under the principal component analysis is the best model. However, under the small sample sizes the SVR type under the factor analysis provided adequate results.
PubDate: 20220602
DOI: 10.18187/pjsor.v18i2.4049
 A New Flexible Probability Model: Theory, Estimation and Modeling Bimodal
Left Skewed Data
Authors: Mohamed Aboraya, M. Masoom Ali, Haitham M. Yousof, Mohamed Ibrahim Mohamed
Pages: 437  463
Abstract: In this work, we introduced a new threeparameter NadarajahHaghighi model. We derived explicit expressions for some of it statistical properties. The Farlie Gumbel Morgenstern, modified Farlie Gumbel Morgenstern, Clayton, Renyi and AliMikhailHaq copulas are used for deriving some bivariate type extensions. We consider maximum likelihood, CramérvonMises, ordinary least squares, whighted least squares, Anderson Darling, right tail Anderson Darling and left tail Anderson Darling estimation procedures to estimate the unknown model parameters. Simulation study for comparing estimation methods is performed. An application for comparing methods as also presented. The maximum likelihood estimation method is the best method. However, the other methods performed well. Another application for comparing the competitive models is investigated.
PubDate: 20220602
DOI: 10.18187/pjsor.v18i2.3938
 Spatialtemporal factors affecting monthly rainfall in some Central Asian
countries assuming a Weibull regression model
Authors: Emerson Barili, Jorge Alberto Achcar, Ricardo Puziol de Oliveira
Pages: 465  482
Abstract: Climate change has been observed worldwide in the last years. Among the different effects of climate change, rain precipitation is one of the effects that most challenge the population of all countries in the world. The main goal of this study is to introduce a data analysis of monthly rainfall data related to five countries in Central Asia (Kazakhstan, Kyrgyzstan, Tadjikistan, Turkmenistan and Uzbekistan) for a long period of time to discover the behavior of rain precipitation in these countries in the last decades and possible link with climate change. Since climate data are positive real values, Weibull regression models are used in the data analysis in presence of some spatial factors as latitude and longitude of the climate stations in each country, temporal factors (linear year effects), altitude of the climate station and categorical factors (countries).The obtained results show that some factors have different effects in the monthly rainfall of the assumed countries during the followup assumed period, possibly linked to the climate change observed in the last decades worldwide.
PubDate: 20220602
DOI: 10.18187/pjsor.v18i2.3976
 A New GeneralizedX Family of Distributions: Applications,
Characterization and a Mixture of Random Effect Models
Authors: Rasool Roozegar, Getachew Tekle, Gholamhossein Hamedani
Pages: 483  504
Abstract: The researchers in applied statistics are recently highly motivated to introduce new generalizations of distributions due to the limitations of the classical univariate distributions. In this study, we propose a new family called new generalizedX family of distributions. A special submodel called new generalizedWeibull distribution is studied in detail. Some basic statistical properties are discussed in depth. The performance of the new proposed model is assessed graphically and numerically. It is compared with the five wellknown competing models. The proposed model is the best in its performance based on the model adequacy and discrimination techniques. The analysis is done for the real data and the maximum likelihood estimation technique is used for the estimation of the model parameters. Furthermore, a simulation study is conducted to evaluate the performance of the maximum likelihood estimators. Additionally, we discuss a mixture of random effect models which are capable of dealing with the overdispersion and correlation in the data. The models are compared for their best fit of the data with these important features. The graphical and model comparison methods implied a good improvement in the combined model.
PubDate: 20220603
DOI: 10.18187/pjsor.v18i2.4043