Browsing by Subject "Regression analysis"

Now showing 1 - 16 of 16

Open Access
Bağlam ağaçları ile ardışık doğrusal olmayan bağlanım
(IEEE, 2014-04) Vanlı, N. Denizcan; Kozat, Süleyman S.
Bu bildiride, ardışık doğrusal olmayan bağlanım problemi incelenmiş ve bağlam ağaçları kullanarak etkili bir öğrenme algoritması sunulmuştur. Bu amaçla, bağlanım alanı parçalara ayrılmış ve oluşan bölgeler bağlam ağacı ile simgelenmiştir. Her bölgede bağımsız bağlanım algoritmaları kullanılarak bağlam ağacı tarafından gösterilebilen tüm doğrusal olmayan modellerin kestirimleri, hesaplama karmaşıklığı bağlam ağacının düğüm sayısıyla doğrusal olan bu algoritma ile uyarlanır olarak birleştirilmiştir. Önerilen algoritmanın performans limitleri, veriler üzerinde istatistiksel varsayımlarda bulunmaksızın incelenmiştir. Ayrıca, teorik sonuçları izah etmek için sayısal bir örnek sunulmuştur.
Open Access
Çağrı merkezi metin madenciliği yaklaşımı
(IEEE, 2017-05) Yiğit, İ. O.; Ateş, A. F.; Güvercin, Mehmet; Ferhatosmanoğlu, Hakan; Gedik, Buğra
Günümüzde çağrı merkezlerindeki görüşme kayıtlarının sesten metne dönüştürülebilmesi görüşme kaydı metinleri üzerinde metin madenciliği yöntemlerinin uygulanmasını mümkün kılmaktadır. Bu çalışma kapsamında görüşme kaydı metinleri kullanarak görüşmenin içeriğinin duygu yönünden (olumlu/olumsuz) değerlendirilmesi, müşteri memnuniyetinin ve müşteri temsilcisi performansının ölçülmesi amaçlanmaktadır. Yapılan çalışmada görüşme kaydı metinlerinden metin madenciliği yöntemleri ile yeni özellikler çıkarılmıştır. Metinlerden elde edilen özelliklerden yararlanılarak sınıflandırma ve regresyon yöntemleriyle görüşme kayıtlarının içeriklerinin değerlendirilmesini sağlayacak tahmin modelleri oluşturulmuştur. Bu çalışma sonucunda ortaya çıkarılan tahmin modellerinin Türk Telekom bünyesindeki çağrı merkezlerinde kullanılması hedeflenmektedir.
Open Access
Data-driven two-stage inventory problem
(2021-09) Çolak, Simay Ayça
In this thesis, we consider two-stage newsvendor problem where the decision maker selling a seasonal product only uses the historical demand information in her decisions. In our setting, there are two decisions to be made: the order quan-tity, and a marked-down price. We decide on how many products to order for the ﬁrst stage, as well as how to set a marked-down price for remaining unsold inventory in the second stage. To solve the problem considered, data-driven mod-els which do not require any distributional assumption are provided. Speciﬁcally, we propose six data-driven methods that solve the problem hierarchically in ad-dition to another method which ﬁnds the order quantity and the marked-down price for the remaining inventory simultaneously by using a mixed integer linear program. We generate the data from selected demand distributions and divide it into a training data and a testing data. The generated data is a function of the way that decisions were made historically. We make a deﬁnition of the relevancy level based on what decisions the data depends on. We conduct a numerical study to evaluate: (a) the eﬀect of data relevancy, (b) the eﬀect of training data size, (c) the performance of proposed models. We investigate the performances of proposed models in three ways: (1) comparison the best model with the worst one, (2) comparison with respective expected values, (3) comparison with respec-tive the inverse coeﬃcient of variation. Lastly, we measure how many times one model is the best among testing samples and compare models based on their performances.
Open Access
Dedollarization in Turkey after decades of dollarization: a myth or reality?
(Elsevier BV, 2007) Özcan, K. M.; Us, V.
The paper analyzes dollarization in the Turkish economy given the evidence on dedollarization signals. On conducting a Vector Autoregression (VAR) model, the empirical evidence suggests that dollarization has mostly been shaped by macroeconomic imbalances as measured by exchange rate depreciation volatility, inflation volatility and expectations. Furthermore, the generalized impulse response function (IRF) analysis, in addition to the analysis of variance decomposition (VDC) gives support to the notion that dollarization seems to sustain its persistent nature, thus hysteresis still prevails. Hence, unfavorable macroeconomic conditions apparently contribute to dollarization while dollarization itself contains inertia. Furthermore, dedollarization that presumably started after 2001 has lost headway after May 2006. Thus, it seems too early to conclude that dollarization changed its route to dedollarization. © 2007 Elsevier B.V. All rights reserved.
Open Access
Differences in the accumulation and distribution profile of heavy metals and metalloid between male and female crayfish (Astacus leptodactylus)
(2013) Tunca, E.; Ucuncu, E.; Ozkan, A.D.; Ulger, Z.E.; Cansizoǧlu, A.E.; Tekinay, T.
Concentrations of selected heavy metals and a metalloid were measured by ICP-MS in crayfish (Astacus leptodactylus) collected from Lake Hirfanli, Turkey. Aluminum (Al), chromium (52Cr, 53Cr), copper ( 63Cu, 65Cu), manganese (Mn), nickel (Ni) and arsenic (As) were measured in the exoskeleton, gills, hepatopancreas and abdominal muscle tissues of 60 crayfish of both genders. With the exception of Al, differences were determined between male and female cohorts for the accumulation trends of the above-mentioned elements in the four tissues. It was also noted that the accumulation rates of Ni and As were significantly lower in gill tissue of females compared to males and no significant difference was observed for Cu isotopes in female crayfish. Cluster Analysis (CA) recovered similar results for both genders, with links between accumulations of Ni and As being notable. Accumulation models were described separately for male and female crayfish using regression analysis, and are presented for models where R2 > 0.85. © 2013 Springer Science+Business Media New York.
Open Access
Estimation of a change point in a hazard function based on censored data
(Springer New York LLC, 2003) Gijbels, I.; Gürler, Ü.
The hazard function plays an important role in reliability or survival studies since it describes the instantaneous risk of failure of items at a time point, given that they have not failed before. In some real life applications, abrupt changes in the hazard function are observed due to overhauls, major operations or specific maintenance activities. In such situations it is of interest to detect the location where such a change occurs and estimate the size of the change. In this paper we consider the problem of estimating a single change point in a piecewise constant hazard function when the observed variables are subject to random censoring. We suggest an estimation procedure that is based on certain structural properties and on least squares ideas. A simulation study is carried out to compare the performance of this estimator with two estimators available in the literature: an estimator based on a functional of the Nelson-Aalen estimator and a maximum likelihood estimator. The proposed least squares estimator turns out to be less biased than the other two estimators, but has a larger variance. We illustrate the estimation method on some real data sets.
Open Access
Experimental and finite element analysis of EDM process and investigation of material removal rate by response surface methodology
(2013) Hosseini Kalajahi, M.; Rash Ahmadi, S.; Nadimi Bavil Oliaei, S.
In this study, thermal modeling and finite element simulation of electrical discharge machining (EDM) has been done, taking into account several important aspects such as temperature-dependent material properties, shape and size of the heated zone (Gaussian heat distribution), energy distribution factor, plasma flushing efficiency, and phase change to predict thermal behavior and material removal mechanism in EDM process. Temperature distribution on the cathode has been calculated using ANSYS finite element code, and the effect of EDM parameters on heat distribution along the radius and depth of the workpiece has been obtained. Temperature profiles have been used to calculate theoretical material removal rate (MRR) from the cathode. Theoretically calculated MRRs are compared with the experimental results, making it possible to precisely determine the portion of energy that enters the cathode for AISI H13 tool steel. Also in this paper, the effect of EDM parameters on MRR has been investigated by using the technique of design of experiments and response surface methodology. Finally, a quadratic polynomial regression model has been proposed for MRR, and the accuracy of this model has been checked by means of analysis of residuals. © 2013 Springer-Verlag London.
Open Access
Income inequality and economic convergence in Turkey: a spatial effect analysis
(Sage Publications, 2009) Yildirim, J.; Öcal, N.; Özyildirim, S.
Even though the convergence of regional per capita income has been a highly debated issue internationally, empirical evidence regarding Turkey is limited as well as contradictory. This article is an attempt to investigate regional income inequality and the convergence dynamics in Turkey for the time period 1987-2001. First, the Theil coefficient of concentration index is used to analyze the dispersion aspects of the convergence process. The geographically based decomposition of inequality suggests a strong correlation between the share of interregional inequality and spatial clustering. Then, we estimate convergence dynamics employing alternative spatial econometric methods. In addition to the global models, we also estimate local models taking spatial variations into account. Empirical analysis indicates that geographically weighted regression improves model fitting with better explanatory power. There is considerable variation in speed of convergence of provinces, which cannot be captured by the traditional beta convergence analysis.
Open Access
Inflation and inflation uncertainty in the G-7 countries
(Elsevier BV, 2005) Berument, Hakan; Dincer, N. N.
This study examines the relationship between inflation and inflation uncertainty in the G-7 countries for the period from 1957 to 2001. The causality between the inflation and inflation uncertainty is tested by using the Full Information Maximum Likelihood Method with extended lags. Our results suggest that inflation causes inflation uncertainty for all the G-7 countries, while inflation uncertainty causes inflation for Canada, France, Japan, the UK and the US. Furthermore, we find that in four countries (Canada, France, the UK and the US) increased uncertainty lowers inflation, and in only one country (Japan), increased uncertainty raises inflation. © 2004 Elsevier B.V. All rights reserved.
Open Access
Mathematical and numerical modeling of the effect of input-parameters on the flushing efficiency of plasma channel in EDM process
(Elsevier Ltd, 2013) Shabgard, M.; Ahmadi, R.; Seyedzavvar, M.; Oliaei, S.N.B.
In the present study, the temperature distribution on the surface of workpiece and tool during a single discharge in the electrical discharge machining process has been simulated using ABAQUS code finite element software. The temperature dependency of material properties and the expanding of plasma channel radius with time have been employed in the simulation stage. The profile of temperature distribution has been utilized to calculate the dimensions of discharge crater. Based on the results of FEM and the experimental observations, a numerical analysis has been developed assessing the contribution of input-parameters on the efficiency of plasma channel in removing the molten material from molten puddles on the surfaces of workpiece and tool at the end of each discharge. The results show that the increase in the pulse current and pulse on-time have converse effects on the plasma flushing efficiency, as it increases by the prior one and decreases by the latter one. Later, the introduced formulas for plasma flushing efficiency based on regression model were utilized to predict the cardinal parameter of recast layer thickness on the electrodes which demands expensive empirical tests to be obtained. © 2012 Elsevier Ltd. All rights reserved.
Open Access
Online distributed nonlinear regression via neural networks
(IEEE, 2017) Ergen, Tolga; Kozat, Süleyman Serdar
In this paper, we study the nonlinear regression problem in a network of nodes and introduce long short term memory (LSTM) based algorithms. In order to learn the parameters of the LSTM architecture in an online manner, we put the LSTM equations into a nonlinear state space form and then introduce our distributed particle filtering (DPF) based training algorithm. Our training algorithm asymptotically achieves the optimal training performance. In our simulations, we illustrate the performance improvement achieved by the introduced algorithm with respect to the conventional methods.
Open Access
Persistency of Turkish export shocks: a quantile autoregression (QAR) approach
(Springer, 2016) Berument, Hakan; Dincer, N. N.; Yasar, P.
This study analyzes the persistency of total and disaggregated Turkish exports for different shock magnitudes using the quantile autoregression (QAR) method in line with Koenker and Xiao (J Am Stat Assoc 99:775–787, 2004). The results suggest that the persistence of shocks are not similar across different quantiles of Total Exports and disaggregated export sectors, indicating an asymmetry in the case of negative and positive shocks across different export sectors. The persistency behavior of Total Exports as well as Food and Beverages, Chemicals, Basic Metals, Raw Materials, Motor Vehicles and Radio & TV exports are asymmetric to negative versus positive shocks, which cannot be captured by traditional unit root tests. Thus, sound interpretation of QAR results is necessary for policy makers to identify shock characteristics and thereby pursue appropriate policies for overcoming adverse impacts on the economy. © 2015, Springer Science+Business Media New York.
Open Access
Piecewise nonlinear regression via decision adaptive trees
(IEEE, 2014-09) Vanlı, N. Denizcan; Sayın, Muhammed O.; Ergüt, S.; Kozat, Süleyman S.
We investigate the problem of adaptive nonlinear regression and introduce tree based piecewise linear regression algorithms that are highly efficient and provide significantly improved performance with guaranteed upper bounds in an individual sequence manner. We partition the regressor space using hyperplanes in a nested structure according to the notion of a tree. In this manner, we introduce an adaptive nonlinear regression algorithm that not only adapts the regressor of each partition but also learns the complete tree structure with a computational complexity only polynomial in the number of nodes of the tree. Our algorithm is constructed to directly minimize the final regression error without introducing any ad-hoc parameters. Moreover, our method can be readily incorporated with any tree construction method as demonstrated in the paper. © 2014 EURASIP.
Open Access
Pulse shape design using iterative projections
(IEEE, 2005-09) Güven, H. Emre; Çetin, A. Enis
In this paper, the pulse shape design for various communication systems including PAM, FSK, and PSK is considered. The pulse is designed by imposing constraints on the time and frequency domains constraints on the autocorrelation function of the pulse shape. Intersymbol interference, finite duration and spectral mask restrictions are a few examples leading to convex sets in L 2. The autocorrelation function of the pulse is obtained by performing iterative projections onto convex sets. After this step, the minimum phase or maximum phase pulse producing the autocorrelation function is obtained by cepstral deconvolution.
Open Access
Support vector networks for prediction of floor pressures in shallow cavity flows
(IEEE, 2007) Efe, M. Ö.; Debiasi, M.; Yan, P.; Özbay, Hitay; Samimy, M.
During the last decade, Support Vector Machines (SVM) have proved to be very successful tools for classification and regression problems. The representational performance of this type of networks is studied on a cavity flow facility developed to investigate the characteristics of aerodynamic flows at various Mach numbers. Several test conditions have been experimented to collect a set of data, which is in the form of pressure readings from particular points in the test section. The goal is to develop a SVM based model that emulates the one step ahead behavior of the flow measurement at the cavity floor. The SVM based model is built for a very limited amount of training data and the model is tested for an extended set of test conditions. A relative error is defined to measure the reconstruction performance, and the peak value of the FFT magnitude of the error is measured. The results indicate that the SVM based model is capable of matching the experimental data satisfactorily over the conditions that are close to the training data collection conditions, and the performance degrades as the Mach number gets away from the conditions considered during training.
Open Access
Transformational leadership and organizational innovation: the roles of internal and external support for innovation
(Wiley-Blackwell Publishing, 2009) Gumusluğlu, L.; Ilsev, A.
Leadership has been suggested to be an important factor affecting innovation. A number of studies have shown that transformational leadership positively influences organizational innovation. However, there is a lack of studies examining the contextual conditions under which this effect occurs or is augmented. Therefore, this study aimed to investigate the impact of transformational leadership on organizational innovation and to determine whether internal and external support for innovation as contextual conditions influence this effect. Organizational innovation was conceptualized as the tendency of the organization to develop new or improved products or services and its success in bringing those products or services to the market. Transformational leadership was hypothesized to have a positive influence on organizational innovation. Furthermore, this effect was proposed to be moderated by internal support for innovation, which refers to an innovation supporting climate and adequate resources allocated to innovation. Support received from external organizations for the purposes of knowledge and resource acquisition was also proposed to moderate the relationship between transformational leadership and organizational innovation. To test these hypotheses, data were collected from 163 research and development (R&D) employees and managers of 43 micro- and small-sized Turkish entrepreneurial software development companies. Two separate questionnaires were used to collect the data. Employees' questionnaires included measures of transformational leadership and internal support for innovation, whereas managers' questionnaires included questions about product innovations of their companies and the degree of support they received from external institutions. Organizational innovation was measured with a market-oriented criterion developed specifically for developing countries and newly developing industries. Hierarchical regression analysis was used to test the hypothesized effects. The results of the analysis provided support for the positive influence of transformational leadership on organizational innovation. This finding is significant because this positive effect was identified in micro- and small-sized companies, whereas previous research focused mainly on large companies. In addition, external support for innovation was found to significantly moderate this effect. Specifically, the relationship between transformational leadership and organizational innovation was stronger when external support was at high levels than when there was no external support. This study is the first to investigate and empirically show the importance of this contextual condition for organizational innovation. The moderating effect of internal support for innovation, however, was not significant. This study shows that transformational leadership is an important determinant of organizational innovation and encourages managers to engage in transformational leadership behaviors to promote organizational innovation. In line with this, transformational leadership, which is heavily suggested to be a subject of management training and development in developed countries, should also be incorporated into such programs in developing countries. Moreover, this study highlights the importance of external support in the organizational innovation process. The results suggest that technical and financial support received from outside the organization can be a more important contextual influence in boosting up innovation than an innovation-supporting internal climate. Therefore, managers, particularly of micro- and small-sized companies, should play external roles such as boundary spanning and should build relationships with external institutions that provide technical and financial support. The findings of this study are especially important for managers of companies that plan to or currently operate in countries with developing economies.