Abstract: Feature selection is an important preprocessing step in analyzing large scale data. In this paper, we prove the monotonicity property of the \(\chi ^2\)-statistic and use it to construct a more robust feature selection method. In particular, we show that \(\chi ^2_{Y, X_1} \le \chi ^2_{Y, (X_1, X_2)}\). This result indicates that a new feature should be added to an existing feature set only if it increases the \(\chi ^2\)-statistic beyond a certain threshold. Our stepwise feature selection algorithm significantly reduces the number of features considered at each stage making it more efficient than other similar methods. In addition, the selection process has a natural stopping point thus eliminating the need for user input. Numerical experiments confirm that the proposed algorithm can significantly reduce the number of features required for classification and improve classifier accuracy. PubDate: 2020-03-25

Abstract: In a multi-objective optimization problem there is more than one objective function and there is no single optimal solution which simultaneously optimizes all of the given objective functions. For these unsuitable conditions the decision makers always search for the most ‘‘preferred’’ solution, in contrast to the optimal solution. A number of mathematical programming methods, namely Weighted-sum method, Goal programming, Lexicographic method, Weighted min–max method, Exponential weighted criterion, Weighted product method, Bounded objective function method and Weighted Tchebycheff optimization methods have been applied in the recent past to find the optimal solution. In this paper weighted Tchebycheff optimization methods has been applied to find the optimal solution of a multi-objective optimization problem. A solution procedure of weighted Tchebycheff technique has been discussed to find the optimal solution of the multi-objective optimization problems. For the most part, the parameters of a multi-objective optimization model are thought to be deterministic and settled. Nonetheless, the qualities watched for the parameters in true multi-objective optimization problems are frequently loose and subject to change. In this way, we utilize multi-objective optimization model inside a vulnerability based system and propose a multi-objective optimization model whose coefficients are uncertain in nature. We accept the uncertain variables (UVs) to have linear uncertainty distributions. Finally, a numerical example is solved weighted Tchebycheff technique. PubDate: 2020-03-23

Abstract: Without the active participation of women in all facets of life economic development cannot be accomplished. There is consensus among scholars that women may play a key role in the phenomenon of entrepreneurship. The proportion of the contribution of women to economic and social development depends on the institutions ' promotion of gender equality and gender blind support. While women make up about fifty per cent of the world’s population, they have less opportunity to control their lives and make decisions than men. Women entrepreneurs have been named to bring prosperity and education to the developing countries as the new growth drivers and the rising stars of economies. The main objective of the analysis was to examine the impact of internal market dynamics, internal market transparency, physical and service infrastructure and cultural and social norms on the forecasting of total and female entrepreneurial activities. Since this is the highly nonlinear job the soft computing approach has been applied in this analysis. The Process for ANFIS (adaptive neuro fuzzy inference system) was applied to determine the most important variables for both total and female entrepreneurial activity. To order to better understand this trend, rapid growth and involvement of women to entrepreneurship and the growing research body creates a need for both general and unique theoretical perspectives and approaches. PubDate: 2020-03-19

Abstract: In this paper, we derive the likelihood function of the neoteric ranked set sampling (NRSS) as dependent in sampling method and double neoteric ranked set sampling (DNRSS) designs as combine between independent sampling method in the first stage and dependent sampling method in the second stage and they compared for the estimation of the parameters of the inverse Weibull (IW) distribution. An intensive simulation has been made to compare the one and the two stages designs. The results showed that likelihood estimation based on ranked set sampling (RSS) as independent sampling method, NRSS and DNRSS designs provide more efficient estimators than the usual simple random sampling design. Moreover, the DNRSS is slightly more efficient than the NRSS and RSS designs in the case of estimating the IW distribution parameters. PubDate: 2020-03-16

Abstract: Classical distributions do not always provide reasonable fit to all forms of datasets, hence the need to generalize existing distributions to enhance their flexibility in modeling of data. The study developed the odd Chen-G family of distributions. It derives the statistical properties of the new family such as the quantile, moments, and order statistics. Though capable of generalizing other distributions, the study proposed three special distributions; odd Chen Burr III, odd Chen Lomax and odd Chen Weibull distributions. The application of the new family is then demonstrated using real data. PubDate: 2020-03-16

Abstract: In this paper, the likelihood estimation of model parameters and acceleration factor are considered under step-stress partially accelerated life test using adaptive type-II progressive hybrid censoring scheme, when the lifetime of the test units follows Exponentiated Pareto distribution. The numerical values of Maximum likelihood estimators are obtained using the Newton–Raphson technique. The performance of model parameters and acceleration factor in terms of mean square errors and biases are evaluated using the Monte-Carlo simulation technique. PubDate: 2020-03-14

Abstract: The bivariate Weibull distribution is an important lifetime distribution in survival analysis. In this paper, Farlie–Gumbel–Morgenstern (FGM) copula and Weibull marginal distribution are used for creating bivariate distribution which is called FGM bivariate Weibull (FGMBW) distribution. FGMBW distribution is used for describing bivariate data that have weak correlation between variables in lifetime data. It is a good alternative to bivariate several lifetime distributions for modeling real-valued data in application. Some properties of the FGMBW distribution are obtained such as product moment, skewness, kurtosis, moment generation function, reliability function and hazard function. Three different estimation methods for parameters estimation are discussed for FGMBW distribution namely; maximum likelihood estimation, inference function for margins method and semi-parametric method. To evaluate the performance of the estimators, a Monte Carlo simulations study is conducted to compare the preferences between estimation methods. Also, a real data set is introduced, analyzed to investigate the model and useful results are obtained for illustrative purposes. PubDate: 2020-03-01

Abstract: Classification is an important task in Machine Learning. Often datasets used for such problems have a large number of features where only a few may be actually useful for this task. Feature Selection is the process where we aim to remove irrelevant features in order to improve our performance. This improved performance could be achieved with an increase in accuracy or by minimizing number of features selected for the task of classification, most Feature Selection algorithms aims at only one of these objectives in their approach. This paper presents the use of Diploid Genetic Algorithm (DGA) on multi-objective optimization of a classification problem for feature selection. The task is to develop a model for solving a Subset Sum Problem using DGA and applying the solution of this problem in order to accomplish the goal of multi-objective optimization by maximizing accuracy using minimum number of features. The model has been applied to publicly available datasets and the results shown are encouraging. This work establishes the veracity of DGA in feature selection. PubDate: 2020-03-01

Abstract: A new class of distributions with increasing, decreasing, bathtub-shaped and unimodal hazard rate forms called generalized quadratic hazard rate-power series distribution is proposed. The new distribution is obtained by compounding the generalized quadratic hazard rate and power series distributions. This class of distributions contains several important distributions appeared in the literature, such as generalized quadratic hazard rate-geometric, -Poisson, -logarithmic, -binomial and -negative binomial distributions as special cases. We provide comprehensive mathematical properties of the new distribution. We obtain closed-form expressions for the density function, cumulative distribution function, survival and hazard rate functions, moments, mean residual life, mean past lifetime, order statistics and moments of order statistics; certain characterizations of the proposed distribution are presented as well. The special distributions are studied in some details. The maximum likelihood method is used to estimate the unknown parameters. We propose to use EM algorithm to compute the maximum likelihood estimators of the unknown parameters. It is observed that the proposed EM algorithm can be implemented very easily in practice. One data set has been analyzed for illustrative purposes. It is observed that the proposed model and the EM algorithm work quite well in practice. PubDate: 2020-03-01

Abstract: This article deals with the constant–stress partially accelerated life test using type I and type II censored data in the presence of competing failure causes. Suppose that the occurrence time of the failure cause follows Weibull distribution. Maximum likelihood technique is employed to estimate the population parameters of the distribution. The performance of the theoretical estimators of the parameters are evaluated and investigated by using a simulation algorithm. PubDate: 2020-03-01

Abstract: In this paper, our main objective is to illustrate the flexibility of the wider class of generalized gamma distribution to model right censored survival data. This distribution contains the commonly used gamma, Weibull, and lognormal distributions as particular cases and this flexibility allows us to carry out a model discrimination, within its class, to choose a lifetime distribution that provides the best fit to a given data. A detailed Monte Carlo simulation study is carried out to display the flexibility of the generalized distribution using likelihood ratio test and information-based criteria. The maximum likelihood estimates of the parameters are obtained by using inbuilt optimization techniques available in R statistical software. We also display the performance of the estimation technique by calculating the bias, mean square error, and coverage probabilities of the confidence intervals for different confidence levels. Finally, we illustrate the advantage of using the generalized gamma distribution using two real datasets and we motivate the use of an extended version of the generalized gamma distribution. PubDate: 2020-03-01

Abstract: In this article, we have proposed the cubic transmuted Pareto distribution, by using the cubic transmuted family of distributions introduced by Rahman et al. (in Pak J Stat Oper Res 14:451–469, 2018). We have explored the distribution in detail and statistical properties of the distribution have been studied. The parameter estimation for the distribution has been discussed and the performance of estimators is studied by conducting extensive simulation study. Finally, the cubic transmuted Pareto distribution has been fitted on two real datasets to investigate it’s applicability. PubDate: 2020-03-01

Abstract: In this article we consider a four parameter extended Burr-III distribution and study some distributional, reliability properties and parameter estimation. Performance of estimation technique used for model parameters estimation is numerically investigated employing Monte Carlo simulation with different sample sizes and parameter values. Efficacy of this distribution in modelling one failure time data is evaluated in comparison to some existing extensions of Bur-III distribution employing well known goodness of fit tests and model selection criteria. Our findings show the proposed distribution as the best among the all the other extensions of Burr-III distribution considered in this study. PubDate: 2020-03-01

Abstract: Women have always faced a number of disadvantageous gaps in the labour market; the status of women at the labour markets throughout the world has not substantially narrowed gender gaps in the workplace. Many women in developing countries are domestic workers or informal factory workers, while others are unpaid workers in family enterprises and family farms. Agriculture is the primary sector of women’s employment; Sub-Saharan Africa is among regions with the highest proportion of women employment in the agriculture sector. This research was conducted on 274 sampled households with the objective to determine the factors associated with women’s employment status and to examine whether the estimated parameters for logistic regression model adopting Bayesian and maximum likelihood estimation approaches are similar or not. The research revealed that about 144 (52.6%) of sampled women were unemployed that is, they were not involved in any activity for earning during the data collection. The inferential analysis using both Bayesian and Maximum likelihood estimation schemes indicated that, pregnancy, age, education level, husband/partner occupation, marital status, family size, training opportunity and a child less than 5 years old had statistically significant (p < 0.05) effect on employment status of women. The maximum likelihood estimates and Bayesian estimates with non-informative prior do not have considerable difference. PubDate: 2020-03-01

Abstract: The alternative proposed method aims to combine management accounting, precisely the activity-based system, and statistical tools to develop a method of assessing and predicting human capital within research laboratory. Statistical tools are Standardized Mean Difference, Hierarchical Cluster Analysis and Discriminant Analysis. The first normalizes the activities of the laboratory; the second classifies the results obtained, while the third standardizes these results by expressing them in terms of probability. The standardized scores are used for the computation and the prediction of human capital in research laboratories via activity regrouping center. The originality of this work is to fill a research gap in the field of hybridization in calculation and prediction of human capital by integrating the two disciplines mentioned above. Likewise, the originality of this work lies in the use of an activity-based accounting architecture to process outputs (and not costs) related to intangible aspects. The proposed method has research and social implications since it allows making appropriate research policy, adequate management control and improves organizational relations within the laboratory concerned. The findings show, through an illustration, the applicability of the proposed method and the usefulness of the tools used to do this. PubDate: 2020-02-20

Abstract: Dara and Ahmad (Recent advances in moment distribution and their hazard rates, Academic Publishing GmbH KG, Lap Lambert, 2012) proposed the length-biased exponential (LBE) distribution and proved that the LBE distribution is more flexible than the exponential distribution. In this paper, we have obtained new explicit algebraic expressions and some recurrence relations for both single and product moments of order statistics from LBE distribution. Further, these expressions are used to compute the means, variances and covariances of order statistics for different sample of sizes and for arbitrarily chosen parameter values. Next, we use these moments to obtain the best linear unbiased estimates of the location and scale parameters based on complete as well as Type-II right censored samples. Finally, we carried out a simulation study to show the application of our results. PubDate: 2020-02-20

Abstract: In this article, we introduce inverse Power Gompertz distribution with three parameters. Some statistical properties are presented such as hazard rate function, quartile, probability weighted (moments), skewness, kurtosis, entropies function, Bonferroni and Lorenz curves and order statistics. The model parameters are estimated by the method of maximum likelihood, least squares, weighted least squares and Cramérvon Mises. Further, Monte Carlo simulations are carried out to compare between all methods. Finally, the extended model is applied on a real data and the results are given and compared to other models. PubDate: 2020-02-18

Abstract: When the load of the failed components within the system shared by the remaining surviving components, the system is called load-sharing system model. The present study deals with the estimation of load-share parameters with Type-I and Type-II failure censored data considering Weibull distribution as the failure time distribution of each component of the system. The maximum likelihood and bootstrap estimates of the parameters, system reliability and hazard rate functions along with estimated errors are obtained. Classical, boot-p and boot-t confidence intervals for the model parameters have been constructed. Assuming informative priors, Bayes estimates and highest posterior density intervals of the reliability parameters are also computed using Markov Chain Monte Carlo methods under symmetric and asymmetric loss functions. For comparing performances of the various point and interval estimates, a simulation study is conducted. Two real datasets analysis is presented to illustrate the applications of the proposed model. PubDate: 2020-02-01

Abstract: We introduce a new lifetime distribution, called the alpha-power transformed extended exponential distribution which generalizes the extended exponential distribution proposed by Nadarajah and Haghighi (Statistics 45:543–558, 2011) to provide greater flexibility in modeling data from a practical point of view. The new model includes the exponential; extended exponential, and \(\alpha \) power transformed exponential (Mahdavi and Kundu in Commun Stat Theory Methods, 2017) distributions as a special case. This distribution exhibits five hazard rate shapes such as constant, increasing, decreasing, bathtub and upside-down bathtub. Various properties of the proposed distribution, including explicit expressions for the quantiles, moments, conditional moments, stochastic ordering, Bonferroni and Lorenz curve, stress–strength reliability and order statistics are derived. The maximum likelihood estimators of the three unknown parameters of alpha-power transformed extended exponential distribution and the associated confidence intervals are obtained. A simulation study is carried out to examine the performances of the maximum likelihood estimates in terms of their bias and mean squared error using simulated samples. Finally, the potentiality of the distribution is analyzed by means of two real data sets. For the two real data sets, this distribution is found to be superior in its ability to sufficiently model the data as compared to the Weibull distribution, Generalized exponential distribution, Marshall–Olkin extended exponentiated exponential distribution and exponentiated Nadarajah–Haghighi distributions. PubDate: 2020-01-20

Abstract: Big data, artificial intelligence, data analytics, machine learning, neural networks are promising prospects in the industry right now and subsequently the posterity for the current technological landscape. Initially, we looked into the overwhelming amount of sectors it is involved in. In the auditing process, we were able to conclude; the sports industry seems to be one of the most promising applications of these modern technologies. Hence, this paper offers a deeper look into how the entire sports industry has been affected in a multi-faceted way. Not only, are the on field antics that have been impacted but also the business implications and immersion of fans. The following is a comprehensive review expanding on the aforementioned aspects. PubDate: 2020-01-11