atıf Evren - Academia.edu (original) (raw)

Papers by atıf Evren

Journal of Administrative Sciences and Policy Studies, 2015

Statistical entropy is a measure of dispersion or spread of a random variable. Especially when th... more Statistical entropy is a measure of dispersion or spread of a random variable. Especially when the random variable is nominal, classical measures of dispersion like standard deviation can not be computed. In such cases, measures of variation, including entropy-based statistics;computed by using cell frequencies of a distributionmust be used. The asymptotic properties of entropy statistics have long been studied in literature. Relative entropy plays an important role in evaluating the degree of fit. In other words, relative entropy is a measure of goodness fit of an empirical distribution to a theoretical or hypothesized distribution. In this study for some frequently-used probability distributions,some relative entropy measures are derived by exploiting additivity property of Kullback-Leibler divergence and Jeffreys divergence. Their asymptotic properties under certain assumptions have been discussed. In the end, by some applications, the close relation between relative entropy statistics and other classical test statistics have been emphasized.

Entropy

The nature of dependence between random variables has always been the subject of many statistical... more The nature of dependence between random variables has always been the subject of many statistical problems for over a century. Yet today, there is a great deal of research on this topic, especially focusing on the analysis of nonlinearity. Shannon mutual information has been considered to be the most comprehensive measure of dependence for evaluating total dependence, and several methods have been suggested for discerning the linear and nonlinear components of dependence between two variables. We, in this study, propose employing the Rényi and Tsallis mutual information measures for measuring total dependence because of their parametric nature. We first use a residual analysis in order to remove linear dependence between the variables, and then we compare the Rényi and Tsallis mutual information measures of the original data with that the lacking linear component to determine the degree of nonlinearity. A comparison against the values of the Shannon mutual information measure is als...

Ankara Üniversitesi Veteriner Fakültesi Dergisi, 2018

Bu çalışmanın amacı, İstanbul'un Çatalca ilçesindeki süt mandacılığı işletmelerinin ekonomik yapı... more Bu çalışmanın amacı, İstanbul'un Çatalca ilçesindeki süt mandacılığı işletmelerinin ekonomik yapılarını ve etkinlik durumlarını belirlemektir. Çalışmanın materyalini, amaca yönelik örnekleme yöntemiyle seçilmiş olan mandacılık işletmelerinden anket yöntemiyle toplanmış, araştırma verileri oluşturmaktadır. İşletmelerde sağılan manda başına yapılan hesaplamada, toplam masraflar içinde, yem % 54.23, işgücü % 25.87, veteriner-sağlık % 1.77, elektrik-su % 2.62, diğer giderler % 0.83, bakım ve onarım % 1.98, amortisman % 10.15 ve genel idare gideri % 2.56 oranında pay almıştır. İşletmelerin ortalama fayda/masraf oranı, 1.27 ve üretilen sütün birim maliyeti 3.31 TL olarak tespit edilmiştir. İşletme etkinliklerinin ölçümü, veri zarflama analizi ile yapılmıştır. Analiz için 3 çıktı ve 5 girdiyle girdi ve çıktı yönelimli CCR modeli uygulanmıştır. Çıktı olarak süt geliri, malak geliri ve envanter değer artışı geliri; girdi olarak ise yem masrafı, işgücü masrafı, veteriner-sağlık masrafı, amortisman masrafı ve elektrik-su masrafları analize dahil edilmiştir. Analiz sonucunda etkin olmayan işletmelerin etkin olması için tavsiye edilebilecek potansiyel iyileştirmeler belirlenmiştir. Araştırma kapsamındaki 32 işletmenin % 53'ünün etkin, % 47'sinin etkin olmadığı belirlenmiştir. Etkinlik değerlerini etkileyen faktörler regresyon analizi ile incelenerek, envanter değer artışı ve işgücü maliyetinin, etkinlik değerleri üzerine etkisinin önemli olduğu (p<0.05) sonucuna varılmıştır. Anahtar sözcükler: Ekonomik analiz, süt mandası, üretim etkinliği, veri zarflama analizi, verimlilik. Efficiency analysis of dairy buffalo enterprises in Çatalca district of İstanbul Summary: The purpose of this study is to determine the efficiencies and economic situations of dairy buffalo enterprises in Çatalca district of Istanbul. Research material was collected by means of a questionnaire from 32 enterprises, determined by purposive sampling method in 2013 production periods. According to calculations made per buffalo milked in enterprises, the shares of expenses for feed, labour, veterinary-health, electricity-water, maintenance and repairment, depreciation, general administration and other things in total expenses consist of 54.23%, 25.87%, 1.77%, 2.62%, 1.98%, 10.15%, 2.56% and 0.83% respectively. The average benefit/cost ratio for enterprises was found to be 1.27, whereas the unit cost of milk was 3.31 TL. The measurement of the efficiencies was realized by data envelopment analysis. In this analysis, input and output oriented CCR model with 3 outputs and 5 inputs was adopted. Milkrevenue, calf-revenue and increase in inventory were included in the analysis as outputs and feeding expense, whereas labor-force, veterinary and health expense, depriciation and electricity-water expenses as inputs. At the end, potential improvements that could be advised for inefficient enterprises were determined. The rations of efficient and inefficient enterprises were found 53% and 47% respectively. The factors that affected efficiency score were modeled by regression analysis. Increase in inventory, labor cost were determined to be two influential factors on efficiency (p<0.05).

Journal of Research in Business

Mean-variance portfolio optimization model has been shown to have serious drawbacks. The model as... more Mean-variance portfolio optimization model has been shown to have serious drawbacks. The model assumes that assets returns are normally distributed that is not valid for most of the markets and portfolios. It also relies on asset’s covariance matrices for the calculation of portfolio’s risk that is open to estimation errors. Moreover, these optimization errors are maximized by the method that result in poor out-of-sample performances. In this study, we propose a new portfolio optimization method based on minimization of Tsallis entropy, which is valid for any underlying distribution. First, we show that the Tsallis entropy can be employed as a risk measure for portfolio analysis. Then we demonstrate the validity of the model by comparing its performance with those mean-variance and minimum-variance portfolios using BIST 30 data.

Herfindahl-Hirschmann Indeksi (HHI), Iktisat yazininda piyasalarda yogunlasma derecesinin belirle... more Herfindahl-Hirschmann Indeksi (HHI), Iktisat yazininda piyasalarda yogunlasma derecesinin belirlenmesinde sikca kullanilmaktadir. Herfindahl-Hirschmann Indeksi ayni zamanda, Tsallis entropisinin ozel bir hali olan Gini Yogunlasma Indeksi (GYI) ile yakindan iliskilidir. Bunun yanisira entropi olculerinden turetilen bazi egemenlik olculeri de piyasalarin rekabetcilik derecelerinin belirlenmesinde kullanilabilirler. Entropi olculerinin asimptotik ornekleme dagilimlarinin belirlenmis olmasi ve entropi olculerinin egemenlik olculeri ile olan yakin iliskisi, egemenlik olculeri icin de dogrudan aralik tahmini ya da hipotez testleri yapilabilmesini olasi kilmaktadir. Bu calismada Turkiye’de basin sektorunun satilan gunluk gazeteler bazinda rekabetci/tekelci yapisi HHI ve entropiden tureyen birkac egemenlik olcusu ile birlikte ele alinmistir. Son olarak nokta tahmini yerine aralik tahminine gitmenin daha yerinde olacagi vurgulanmistir.

Communications in Statistics - Simulation and Computation, 2019

Developing technology shows how useful fuzzy inference systems in lots of applications. Fuzzy fun... more Developing technology shows how useful fuzzy inference systems in lots of applications. Fuzzy functions approach which is one of the important fuzzy inference system for time series forecasting. In fuzzy functions approach, the membership values and their non-linear transformations are used together with original input variables to increase the prediction power. However, multicollinearity problem can be occured because of using these correlated variables. Purpose of the paper is to propose a new fuzzy forecasting method with intuitionistic fuzzy sets which has addition information known as hesitation degree. In this case, both intuitionistic fuzzy sets and their non-linear transformations is used to increase the prediction power. Ridge regression method is preferred to obtain intuitionistic fuzzy functions without exposed to multicolinearity problem. To demonstrate the performances of proposed method, some real world time series data are used and the results have shown that the effectiveness of the proposed method in conrast to other methods.

Journal of Applied Statistics, 2021

This study intends to provide a new insight into the concentration and dominance indices as the c... more This study intends to provide a new insight into the concentration and dominance indices as the concerns grow about the increasing concentration in the markets around the world. Most of the studies attempting to measure concentration or dominance in a market employ the popular concentration/dominance indices like Herfindahl–Hirschmann, Hannah–Kay, Rosenbluth–Hall–Tidemann and Concentration ratio. On the other hand, measures of qualitative variation are closely related to entropy, diversity and concentration/dominance measures. In this study, two normalized dominance measures that can be derived from the work of Wilcox on qualitative variation are proposed. The limiting distributions of these normalized dominance measures are formulated. By some simulations, asymptotic behaviors of these indices are analyzed under some assumptions about the market structure. In the end, by an application on the Turkish car sales in 2019, it is determined that the values of dominance indices vary in a considerably large range. Thus one of the dominance indices is determined to have the advantage of having less error in estimation, less sensitivity to smaller market shares, and less sampling variability.

Eurasian Journal of Veterinary Sciences, 2019

Çalışmanın amacı, Türkiye'de faaliyet gösteren büyük ölçekli balıkçıların üretim etkinliklerinin ... more Çalışmanın amacı, Türkiye'de faaliyet gösteren büyük ölçekli balıkçıların üretim etkinliklerinin hesaplanarak, etkinliklerinin arttırılmasına katkı sağlamaktır. Gereç ve Yöntem: Araştırmanın analizleri için, Türkiye İstatistik Kurumu'nun (TÜİK) balıkçı gemilerine ait kayıtları kullanılmıştır. Kullanılan kayıtlar, Türkiye'de avcılık yapan, 13 m ve üzerinde gemi uzunluğuna sahip balıkçı gemilerinin, 2014 üretim yılına ait ekonomik verilerini kapsamaktadır. Araştırmaya dahil edilen 107 adet gemi basit tesadüfi örnekleme yöntemine göre seçilmiştir. Etkinliklerin belirlenmesinde Veri Zarflama Analizinden (VZA) yararlanılmıştır. Veri Zarflama Analizinde veriler, girdi yönelimli, ölçeğe göre sabit getiri (CRS) modeline göre analiz edilmiştir. Girdi olarak akaryakıt, işgücü, tamir bakım, kumanya, kasa buz, giyim, diğer masraflar ve sabit varlık masrafları, çıktı olarak, balık geliri alınmıştır. Bulgular: Analiz sonuçları balıkçıların %27'sinin etkin olduğunu göstermiştir. Etkin olmayan balıkçıların etkin düzeye ulaşabilmesi için tavsiye edilebilecek potansiyel iyileştirme oranları belirlenmiştir. Balıkçıların, akaryakıt, işgücü, tamir-bakım, kumanya, kasa-buz, giyim, diğer ve sabit masraflarını, sırasıyla % 59.27, %55.93, %60.87, %51.17, %43.17, %64.19, %59.50 ve %60.14 oranında azaltırlarsa etkin düzeye gelebilecekleri belirlenmiştir. Öneri: Sorunları çözebilmek için, balıkçılık işletmelerinin, girdi masraflarının azalmasını ve rekabet gücünün artmasını sağlayan devlet teşvik ve destekleri arttırılarak devam ettirilmelidir. Ayrıca örgütlenmenin sağlanabilmesi ve geliştirilmesi için, balıkçılara verilecek eğitimin yanı sıra Su Ürünleri Kooperatifleri güçlendirilerek etkin çalışmaları özendirilmelidir.

International Journal of Engineering and Applied Sciences (IJEAS), 2019

In simple regression analysis, the dependent variable is assumed to have constant variance at dif... more In simple regression analysis, the dependent variable is assumed to have constant variance at different levels of independent variable. Whenever the assumption of constant variance fails, some remedies like the weighted least squares, or Box-Cox transformation may be helpful. While Box-Cox approach is based on a nonlinear transformation on the dependent variable, in the weighted least squares methodology, independent variable is rescaled by weights to maintain constant variance. Although there is already a large literature on this issue, determining the weights seems a major problem. In this study, the weights are alternatively calculated by entropy approach, since statistical entropy, and variance conveys similar information about a probability distribution. In this study, by exploiting the normality assumption of linear models, the weights are determined by the reciprocals of Shannon, Tsallis and Renyi entropies of normal distribution. The weighting procedure has been applied on some simulated data having nonconstant variance. In some applications we have shown that weighting by Tsallis and/or Rényi entropies produced better goodness of fit results in terms of coefficient of determination, and the mean square error.

Applied Intelligence, 2017

Forecasting the future values of a time series is a common research topic and is studied using pr... more Forecasting the future values of a time series is a common research topic and is studied using probabilistic and non-probabilistic methods. For probabilistic methods, the autoregressive integrated moving average and exponential smoothing methods are commonly used, whereas for non-probabilistic methods, artificial neural networks and fuzzy inference systems (FIS) are commonly used. There are numerous FIS methods. While most of these methods are rule-based, there are a few methods that do not require rules, such as the type-1 fuzzy function (T1FF) approach. While it is possible to encounter a method such as an autoregressive (AR) model integrated with a T1FF, no method that includes T1FF and the moving average (MA) model in one algorithm has yet been proposed. The aim of this study is to improve forecasting by taking the disturbance terms into account. The input dataset is organized using the following variables. First, the lagged values of the time series are used for the AR model. Second, a fuzzy c-means clustering algorithm is used to cluster the inputs. Third, for the MA, the residuals of fuzzy functions are used. Hence, AR, MA, and the degree of memberships of the objects are included in the input dataset. Because the objective function is not derivative, particle swarm optimization is preferable for solving it. The results on several datasets show that the proposed method outperforms most of the methods in literature.

Journal of Selcuk University Natural and Applied Science, Jan 10, 2013

Some of the entropy measures proposed are Shannon entropy(1948), Renyi entropy (1961), Havrda&a... more Some of the entropy measures proposed are Shannon entropy(1948), Renyi entropy (1961), Havrda&Charvat entropy(1967), and Tsallis entropy (1988). The limit of Renyi divergence is relative entropy (or Kullback-Leibler divergence) which is a measure of discrepancy between two statistical hypotheses or two probability distributions. Jeffreys’ divergence is a measure of difficulty of making a discrimination between two probability distributions. These divergence measures are related to some chi-square distributions asymptotically such that they can be used in some hypothesis tests. In this study I try to show that entropy based statistics like Kullback-Leibler divergence and Jeffreys’ divergence can be used in some statistical hypothesis tests for multinomial populations by some examples.

Journal of Selcuk University Natural and Applied Science, Apr 1, 2012

Fuzzy nonlinear regression (FNR) is different from classic regression models just because its out... more Fuzzy nonlinear regression (FNR) is different from classic regression models just because its output consists of fuzzy numbers. Predictions are realized by FNR models for the cases in which both input variables are nonlinearly related and output variable is fuzzy. Besides, a FNR model may be used to construct a probability interval for the output variable precisely. It is important to note that an entropy -based approach to FNR models results in smaller propagations for fuzzy intervals.

There are various statistics to measure the degree of association between qualitative variables i... more There are various statistics to measure the degree of association between qualitative variables in literature. Among them, some to mention are Pearson p (the coefficient of contingency), phi-square, Tschuprow’s contingency coefficient, and Cramér’s contingency coefficient. In addition, statistics derived from the concept of entropy like mutual information, Kullback-Leibler divergence and Jeffreys divergence can also be used in measuring association.

Goodness of fit tests can be categorized under several ways. One categorization may be due to the... more Goodness of fit tests can be categorized under several ways. One categorization may be due to the differences between observed and expected frequencies. The other categorization may be based upon the differences between some values of distribution functions. Still the other one may be based upon the divergence of one distribution from the other. Some widely used and well known divergences like Kullback-Leibler divergence or Jeffreys divergence are based on entropy concepts. In this study, we compare some basic goodness of fit tests in terms of their statistical properties with some applications. Keywords: Measures for goodness of fit, likelihood ratio, power divergence statistic, Kullback-Leibler divergence, Jeffreys' divergence, Hellinger distance, Bhattacharya divergence.

Since distributions of qualitative variables can be represented by multinomial distributions, the... more Since distributions of qualitative variables can be represented by multinomial distributions, the role of multinomial distribution in entropy considerations is essential in statistics. Moreover for larger sample sizes multinomial distributions can be approximated well by multivariate normal distributions. The measures of qualitative variations depend on either class frequencies or some functional forms of class frequencies. Therefore the connection between qualitative variation statistics and normality seems straightforward for larger sample sizes. Asymptotic distributions of Shannon, Rényi and Tsallis entropies make some hypothesis testing and inferential techniques applicable to qualitative variations because some entropy measures are also frequently used in qualitative variation calculations. In this study, first we will give few examples of such applications by three entropy measures. Then we make a comparison between the performances of these three entropy measures. Finally, th...

Bu calismanin amaci, Istanbul’un Catalca ilcesindeki sut mandaciligi isletmelerinin ekonomik yapi... more Bu calismanin amaci, Istanbul’un Catalca ilcesindeki sut mandaciligi isletmelerinin ekonomik yapilarini ve etkinlik durumlarini belirlemektir. Calismanin materyalini, amaca yonelik ornekleme yontemiyle secilmis olan mandacilik isletmelerinden anket yontemiyle toplanmis, arastirma verileri olusturmaktadir. Isletmelerde sagilan manda basina yapilan hesaplamada, toplam masraflar icinde, yem % 54.23, isgucu % 25.87, veteriner-saglik % 1.77, elektrik-su % 2.62, diger giderler % 0.83, bakim ve onarim % 1.98, amortisman % 10.15 ve genel idare gideri % 2.56 oraninda pay almistir. Isletmelerin ortalama fayda/masraf orani, 1.27 ve uretilen sutun birim maliyeti 3.31 TL olarak tespit edilmistir. Isletme etkinliklerinin olcumu, veri zarflama analizi ile yapilmistir. Analiz icin 3 cikti ve 5 girdiyle girdi ve cikti yonelimli CCR modeli uygulanmistir. Cikti olarak sut geliri, malak geliri ve envanter deger artisi geliri; girdi olarak ise yem masrafi, isgucu masrafi, veteriner-saglik masrafi, amort...

This paper discusses the applicability of Bayesian multinomial logistic regression model on the p... more This paper discusses the applicability of Bayesian multinomial logistic regression model on the prediction of happiness of Somaliland youth by two variables; age and educational level. It presents two approximate methods on multinomial logistic regression estimation; classical method and Bayesian method or Markov Chain Monte Carlo (MCMC), to obtain the marginal posterior density for the parameters. A comparison of these two methods is carried out to determine the usefulness of Bayesian method on multinomial logistic regression estimation. R and WinBUGS (Bayesian Inference using Gibbs Sampling) programs have been used to fit the model. As both of these two methods have suggested; happiness increases with educational level and decreases with age. In addition, it is also shown that Bayesian Multinomial logistic regression is useful in direct computations and it produces very accurate approximations to the posterior density.