Yazar "Altinisik, Yasin" seçeneğine göre listele
Listeleniyor 1 - 12 / 12
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A COMPARATIVE STUDY ON THE PERFORMANCE OF FREQUENTIST AND BAYESIAN ESTIMATION METHODS UNDER SEPARATION IN LOGISTIC REGRESSION(Ankara Univ, Fac Sci, 2020) Altinisik, YasinSeparation is one of the most commonly encountered estimation problems in the context of logistic regression, which often occurs with small and medium sample sizes. The method of maximum likelihood (MLE; [8]) provides spuriously high parameter estimates and their standard errors under separation in logistic regression. Many researchers in social sciences utilize simple but ad-hoc solutions to overcome this issue, such as doing nothing strategy, removing variable(s) from the model, and combining the levels of the categorical variable in the data causing separation etc. The limitations of these basic solutions have motivated researchers to use more appropriate and innovative estimation techniques to deal with the problem. However, the performance and comparison of these techniques have not been fully investigated yet. The main goal of this paper is to close this research gap by comparing the performance of frequentist and Bayesian estimation methods for coping with separation. A simulation study is performed to investigate the performance of asymptotic, bootstrap-based, and Bayesian estimation techniques with respect to bias, precision, and accuracy measures under separation. In line with the simulation study, a real-data example is used to illustrate how to utilize these methods to solve separation in logistic regression.Öğe Addressing overdispersion and zero-inflation for clustered count data via new multilevel heterogenous hurdle models(Taylor & Francis Ltd, 2023) Altinisik, YasinUnobserved heterogeneity causing overdispersion and the excessive number of zeros take a prominent place in the methodological development on count modeling. An insight into the mechanisms that induce heterogeneity is required for better understanding of the phenomenon of overdispersion. When the heterogeneity is sourced by the stochastic component of the model, the use of a heterogenous Poisson distribution for this part encounters as an elegant solution. Hierarchical design of the study is also responsible for the heterogeneity as the unobservable effects at various levels also contribute to the overdispersion. Zero-inflation, heterogeneity and multilevel nature in the count data present special challenges in their own respect, however the presence of all in one study adds more challenges to the modeling strategies. This study therefore is designed to merge the attractive features of the separate strand of the solutions in order to face such a comprehensive challenge. This study differs from the previous attempts by the choice of two recently developed heterogeneous distributions, namely Poisson-Lindley (PL) and Poisson-Ailamujia (PA) for the truncated part. Using generalized linear mixed modeling settings, predictive performances of the multilevel PL and PA models and their hurdle counterparts were assessed within a comprehensive simulation study in terms of bias, precision and accuracy measures. Multilevel models were applied to two separate real world examples for the assessment of practical implications of the new models proposed in this study.Öğe An AIC-type information criterion evaluating theory-based hypotheses for contingency tables(Springer, 2025) Altinisik, Yasin; Hessels, Roy S.; Van Lissa, Caspar J.; Kuiper, Rebecca M.Researchers face inevitable difficulties when evaluating theory-based hypotheses in the context of contingency tables. Log-linear models are often insufficient to evaluate such hypotheses, as they do not provide enough information on complex relationships between cell probabilities in many real-life applications. These models are usually used to evaluate the relationships between variables using only equality restrictions between model parameters, while specifying theory-based hypotheses often also requires inequality restrictions. Moreover, high-dimensional contingency tables generally contain low cell counts and/or empty cells, complicating parameter estimation in log-linear models. The presence of many parameters in these models also causes difficulties in interpretation when evaluating the hypotheses of interest. This study proposes a method that simplifies evaluating theory-based hypotheses for high-dimensional contingency tables by simultaneously addressing each of the above problems. With this method, theory-based hypotheses, which are specified using equality and/or inequality constraints with respect to (functions of) cell probabilities, are evaluated using an AIC-type information criterion, GORICA. We conduct a simulation study to evaluate the performance of GORICA in the context of contingency tables. Two empirical examples illustrate the use of the method.Öğe Evaluation of Inequality Constrained Hypotheses Using a Generalization of the AIC(Amer Psychological Assoc, 2021) Altinisik, Yasin; Van Lissa, Caspar J.; Hoijtink, Herbert; Oldehinkel, Albertine J.; Kuiper, Rebecca M.In the social and behavioral sciences, it is often not interesting to evaluate the null hypothesis by means of a p-value. Researchers are often more interested in quantifying the evidence in the data (as opposed to using p-values) with respect to their own expectations represented by equality and/or inequality constrained hypotheses (as opposed to the null hypothesis). This article proposes an Akaike-type information criterion (AIC; Akaike, 1973, 1974) called the generalized order-restricted information criterion approximation (GORICA) that evaluates (in)equality constrained hypotheses under a very broad range of statistical models. The results of five simulation studies provide empirical evidence showing that the performance of the GORICA on selecting the best hypothesis out of a set of (in)equality constrained hypotheses is convincing. To illustrate the use of the GORICA, the expectations of researchers are investigated in a logistic regression, multilevel regression, and structural equation model. Translational Abstract Evaluation of Inequality Constrained Hypotheses Using a Generalization of the AIC: Researchers are interested in evaluating equality and/or inequality constrained hypotheses in the context not only of normal linear models, but also of the families outside of normal linear models using a suitable information criterion. However, the available information criteria in the literature are not capable of evaluating (in) equality constrained hypotheses under such a broad range of statistical models. The main aim of this paper is to close this research gap by proposing a new information criterion named the GORICA which can be utilized to evaluate these hypotheses for generalized linear (mixed) models and structural equation models. The GORICA enables researchers to quantify the evidence in the data for two or more (in) equality constrained hypotheses. Like all the other information criteria, the GORICA has the log likelihood and penalty parts. The superiority of the GORICA over the other information criteria lies behind the use of a simple formula when calculating its log likelihood. We investigated the performance of the GORICA on choosing the true hypothesis out of a set of competing hypotheses using simulation studies for logistic regression, multilevel regression, and structural equation model. The findings in these simulation studies suggest that the GORICA has a convincing performance on choosing the true hypothesis. The use of the GORICA is illustrated for (real) data sets in line with these simulation studies.Öğe EXPONENTIATED GENERALIZED RAMOS-LOUZADA DISTRIBUTION WITH PROPERTIES AND APPLICATIONS(Ankara Univ, Fac Sci, 2024) Altinisik, Yasin; Cankaya, EmelIn this paper, we propose a new generalization of Ramos-Louzada (RL) distribution based on two additional shape parameters. Along with the genesis of its distributional form, the derivation of cumulative density function (cdf), survival and hazard rate functions, the quantile function (qf), moments, moment generating function (mgf), Shannon and Renyi entropies, order statistics and a linear representation of the proposed distribution are inspected. Several estimation methods of the model parameters are discussed throughout two comprehensive simulation studies conducted to compare its performance against some lifetime distributions. Application of a real dataset is presented to illustrate the potentiality of this distribution in line with the simulation studies.Öğe INVESTIGATION OF THE EFFECT OF SOCIAL DISTANCE ON FREQUENCY AND VOLTAGE FLUCTUATIONS ON IDENTICAL OCIMUM BASILICUM L. PL ANTS INDOORS AND OUTDOORS FOR 24 HOURS USING A MIXED MODEL(Pakistan Botanical Soc, 2023) Bardak, Selahattin; Altinisik, Yasin; Bursalioglu, Ertugrul OsmanPlants play a vital role in environmental cleanliness by reducing harmful gases in the atmosphere. Genus Ocimum has a separate prescription due to its ability to clean air toxins in the interior. Ocimum has spread commercially all over the world due to its economic importance. Frequency and electrical voltage were measured on the leaves of two identical Ocimum basilicum L. , plants using an oscilloscope for two consecutive days. Interaction between plants was quantified by standard deviations (SDs) of the average voltage and frequency values. A higher standard deviation for these measures means that the plants interact better with each other for the corresponding position (i.e. , adjoining or social distance) and environment (i.e. , indoors or outdoors). The most fluctuating average voltage and frequency values were observed outdoors in the social distance position (SD = 5185.44mV) and outdoors in the adjoining position (SD = 3.01Hz). The smallest variations in average voltage values were obtained indoors at the social distance position (SD = 578.78mV). The average frequency values were in line with each other for the adjacent plants indoors (SD = 0.49Hz) , the social distance plants indoors (SD = 0.36Hz) and the social distance plants outdoors (SD = 0.40Hz). A mixed-modeling framework was used to investigate the effects of position , temperature , humidity and their interaction on the frequency and voltage values. These variables did not have a significant effect on the frequency and voltage values at the outdoor environment. Social distance had a positive effect on voltage values (/1 = 0.25, P = 0.033) indoors. Temperature had a negative impact on frequency values (/2 =-2.09, P = 0.040) and voltage values (/2 =-2.87, P = 0.005) indoors. Similarly , humidity negatively affected the frequency values (/3 =-1.26 , P = 0.033) and voltage values (/3 =-1.74, P = 0.003) indoors. The interaction effect between temperature and humidity was positive for both the frequency values (/4 = 0.04, P = 0.026) and voltage values (/4 = 0.06, P = 0.003) indoors.Öğe New zero-inflated regression models with a variant of censoring(Brazilian Statistical Association, 2022) Altinisik, Yasin; Cankaya, EmelThere is ever growing demand of modeling overdispersed count data generated by various disiplines. Excessive number of zeros and hetero-geneity in the population are two main sources of the overdispersion problem. Development of new count models that are more flexible than conventional Poisson model is thus necessary in order to address such sources. This study fullfils this need by proposing a new heterogeneous Poisson model with a cap-ture of excess zeros, namely zero-inflated Poisson-Ailamujia (ZIPA) model. In line with the aim of curing overdispersion, a censored variant of this newly suggested model is also here developed. An extensive simulation study is conducted to assess the performances of both forms of new models in terms of bias, precision and accuracy measures. Additionally, two real world ap-plications are presented to illustrate practical implications of zero-inflated (censored) Poisson-Ailamujia models in comparison to some alternatives.Öğe PER3 VNTR GENOTYPES MAY PREDICT OVERALL SURVIVAL IN BLADDER CANCER PATIENTS IN THE TURKISH POPULATION(2020) Yeğin, Zeynep; Ozen, Filiz; Altinisik, Yasin; Yıldırım, Ibrahım Halıl; Yildirim, AsifCircadian genes were proven to play significant roles in tumor development and progression via coordinating various cellular processes. Though circadian rhythm disturbances both on the level of expression and genetic variant analysis have been associated with increased risk for many cancer types, none has investigated the potential effect of PER3 VNTR in bladder tumorigenesis yet. In this study, we aimed to assess PER3 VNTR’s effect in terms of creating susceptibility to bladder carcinoma formation. Our second target was to enlighten the possible associations between PER3 genotypes and clinicopathological correlations in bladder carcinoma cohort and thus evaluate outcomes in bladder carcinoma prognosis. In this case-control study, 116 patients and 120 healthy controls were recruited. DNA was isolated from peripheral blood using the standard salting-out procedure and PER3 VNTR variants (ins/del polymorphism) were determined with PCR technique to distinguish the 5-repeats allele (401 bp) from the 4-repeats allele (347 bp). Though this exploratory analysis did not provide evidence supporting the role of PER3 VNTR in the onset of bladder carcinoma, it enabled us to make a risk assessment for the prognosis of bladder carcinoma patients. The survival times of patients decreased in the patient group (progression and cystectomy positive) for PER3 4/4 genotype and (recurrence, progression and cystectomy positive) for PER3 4/5 genotype. Results presented in this study are highly recommended to be investigated and validated in larger samples in different populations and ethnicities to generalize potential clinical utility.Öğe Performance evaluation of estimators in the presence of outliers or omitted predictors: a study on the Poisson-Exponential regression model(Taylor & Francis Inc, 2023) Altinisik, Yasin; Aydin, DemetThe Poisson regression model is vulnerable for overdispersion in the data when estimating model parameters and their standard errors. Overdispersion may occur due to outliers in the data and/or removal of important predictors from the model. This paper employs a regression model that can be used to better cope with outliers and omitted predictor bias in count data compared to the Poisson regression model, namely the Poisson exponential (PE) model which is a reparameterization of the geometric regression model. Along with investigating the distributional properties of the PE distribution, the usual maximum likelihood (ML-I), maximum likelihood with Expectation-maximization algorithm (ML-II), least-square (LS), weighted least-square (WLS), least-absolute deviation (LAD), weighted least-absolute deviation (WLAD), and Cramer-von mises (CVM) estimation methods are utilized in the context of the PE regression model. The performance of these estimation methods with the PE regression model are inspected through two comprehensive simulation studies. The first is conducted on data sets with and without outliers. The second investigates the performance of the estimation methods for the PE regression model with and without omitted predictors. Two real-life applications illustrate the applicability of the PE regression model with the estimation methods for these two situations.Öğe The Proposal of Gamma Folded-Normal Distribution(2022) Altinisik, Yasin; Ceylan, Tahir; Cankaya, EmelDevelopment of new flexible distributions for modeling non-negative measurements occuring in lifetime or reliability studies is a prominent research area in Statistics. As being the most favoured positive definite form, the Gamma distribution poses a basis for such improvements. It is well known that transforming a Gamma variable with another continuous random variable (X) creates Gamma-X family of distributions. Following this principle, we here attempted to define the X variable as Folded-Normal distributed which is also positive definite so as to propose a new family of distributions. Named as Gamma Folded-Normal distribution (GFN), our proposal is a generalization of Gamma Half-Normal distribution and contains more freely estimated parameters. This study evaluates some mathematical properties of GFN distribution such as moments and illustrates the estimation procedure for unknown parameters through a simulation study. A separate simulation is also conducted to compare the performance of this new distribution with the Folded-Normal, Half-Normal and Gamma Half-Normal distributions. Besides, the practical importance of our new proposal is illustrated by analyzing a real world data set.Öğe The role of mother-child relationship between young children's anxiety and social play(Routledge Journals, Taylor & Francis Ltd, 2022) Aslan, Ozge Metin; Altinisik, YasinThe aim of this study was to explore the moderating role of mother-child relationships (closeness and conflict) in the relations between children's anxiety and play behaviour in the sample of Turkish preschool children. Participants were N = 211 children (117 boys, M age = 64.08 months, SD = 12.26) attending preschool from suburban areas in Ankara. Mothers rated children's anxiety and mother-child relationships, whereas teachers provided ratings of children's social play. Among the results, children's anxiety and mother's conflict was positively correlated with reticence behaviour and negatively correlated with social play. Moreover, mother-child closeness significantly moderated these associations. The current findings suggest that mother - child relationships moderated the association between unsociability and social play in children (buffering effect). The interaction between anxiety and mother-child closeness could be beneficial for predicting unsociable children's social play behaviour. Mothers can improve their relationship depending on unsociable children to provide nurturing social play behaviour. Limitations and future directions of the current study are discussed.Öğe Why people vote for thin-centred ideology parties? A multi-level multi-country test of individual and aggregate level predictors(Public Library Science, 2022) Cakal, Huseyin; Altinisik, Yasin; Gokcekus, Omer; Eraslan, Ertugrul GaziThe present research investigates the individual and aggregate level determinants of support for thin-centred ideology parties across 23 European countries. Employing a multilevel modelling approach, we analysed European Social Survey data round 7 2014 (N = 44000). Our findings show that stronger identification with one's country and confidence in one's ability to influence the politics positively but perceiving the system as satisfactory and responsive; trusting the institutions and people, and having positive attitudes toward minorities, i.e., immigrants and refugees, negatively predict support for populist and single issue parties. The level of human development and perceptions of corruption at the country level moderate these effects. Thus, we provide the first evidence that the populist surge is triggered by populist actors' capacity to simultaneously invoke vertical, ordinary people against the elites, and horizontal, us against threatening aliens, categories of people as well as the sovereignty of majority over minorities. These categories and underlying social psychological processes of confidence, trust, and threats are moderated by the general level of human development and corruption perceptions in a country. It is, therefore, likely that voting for populist parties will increase as the liberally democratic countries continue to prosper and offer better opportunities for human development. Stronger emphasis on safeguarding the integrity of the economic and democratic institutions, as our findings imply, and preserving their ethical and honest, i.e., un-corrupt, nature can keep this surge under check.
