University of TehranJournal of Sciences, Islamic Republic of Iran1016-110435320240801Bayesian Clustering of Spatially Varying Coefficients Zero-Inflated Survival Regression Models20521910070710.22059/jsciences.2024.383129.1007886ENSepidehAsadiDepartment of Statistics, Tarbiat Modares University, Tehran, Islamic Republic of IranMohsenMohammadzadehDepartment of Statistics, Tarbiat Modares University, Tehran, Islamic Republic of IranJournal Article20241002The study addresses the challenges of analyzing time-to-event data, particularly emphasizing the discrete nature of durations, such as the number of years until divorce. This frequently results in zero-inflated survival data characterized by a notable frequency of zero observations. To address this, the study employs the zero-inflated discrete Weibull regression (ZIDWR) model, which serves as a suitable framework for evaluating the impact of explanatory variables in survival analysis. However, challenges such as nonstationarity in the relationship between variables and responses and spatial heterogeneity across geographical regions can result in a model with too many parameters To mitigate this, we propose a spatial clustering approach to summarize the parameter space. This Paper leverages nonparametric Bayesian methods to explore the spatial heterogeneity of regression coefficients, focusing on the geographically weighted Chinese restaurant process (gwCRP) for clustering the parameters of the ZIDWR model. Through simulation studies, the gwCRP method outperforms unsupervised clustering algorithms clustering K-means and the standard Chinese restaurant process (CRP), exhibiting superior accuracy and computational efficiency, particularly in scenarios with imbalanced cluster sizes. This improved performance is quantitatively demonstrated through higher Rand indices, lower average mean squared error (AMSE) in parameter estimation and superior log pseudo-marginal likelihood (LPML) values. Applying this methodology to Iranian divorce data reveals distinct spatial clusters characterized by varying covariate effects on the probability of divorce within the first five years of marriage and the subsequent time to divorce.https://jsciences.ut.ac.ir/article_100707_9e6e327290724285a71baadff0bb25b7.pdfUniversity of TehranJournal of Sciences, Islamic Republic of Iran1016-110435320240801Modeling Some Repeated Randomized Responses22123110070910.22059/jsciences.2025.382724.1007885ENMahtabTarhaniDepartment of Statistics, Faculty of Mathematical Sciences and Computer, Shahid Chamran University of Ahvaz, Ahvaz, Islamic Republic of IranMohammad RezaZadkaramiDepartment of Statistics, Faculty of Mathematical Sciences and Computer, Shahid Chamran University of Ahvaz, Ahvaz, Islamic Republic of IranSayad Mohammad RezaAlaviDepartment of Statistics, Faculty of Mathematical Sciences and Computer, Shahid Chamran University of Ahvaz, Ahvaz, Islamic Republic of IranJournal Article20240925Some social surveys address sensitive topics for which respondents do not report reliable responses. Randomized response techniques (RRTs) are employed to increase privacy levels and provide honest answers. However, estimates obtained from this method tend to exhibit increased variances. Repeating randomized responses for each individual increases the sample size, and the mean of observations for each individual reduces the variance of the parameter’s estimator, bringing them closer to reality. In this study, considering continuous additive repeated randomized responses (RRRs), we apply the averaged RR of each individual using the linear regression model for sensitive variable mean. Data on the income of family heads were collected from students, and each respondent was asked to randomize their responses five times. The maximum likelihood estimators of parameters are obtained by two methods. In the first method, the response variable is the first reported observation, and in the second method, we considered the averaged RR for each individual. The results emphasize that the estimators from the second method are closer to reality and have lower variance.https://jsciences.ut.ac.ir/article_100709_fba8847f09af35a03f0348a47e60f423.pdfUniversity of TehranJournal of Sciences, Islamic Republic of Iran1016-110435320240801Bounds for the Varentropy of Basic Discrete Distributions and Characterization of Some Discrete Distributions23324110085010.22059/jsciences.2025.379169.1007870ENFaranakGoodarziDepartment of Statistics, Faculty of Mathematical Sciences, University of Kashan, Kashan, Islamic Republic of Iran0000-0002-3783-6632Journal Article20240709Given the importance of varentropy in information theory, and since a closed form cannot be derived for some discrete distributions, we aim to establish bounds for the varentropy of these distributions and introduce the past varentropy for discrete random variables. In this article, we first acquired lower and upper bounds for the varentropy of the Poisson, binomial, negative binomial, and hypergeometric distributions. Since the resulting upper bounds are expressed as squared logarithmic expectations, we provide an equivalent formulation using squared logarithmic difference coefficients. Similarly, we present lower bounds in terms of logarithmic difference coefficients. Furthermore, an upper bound is derived for the variance of a function of discrete reversed residual lifetime function. We also investigate inequalities involving moments of selected functions via the reversed hazard rate and characterize certain discrete distributions by the Cauchy-Schwarz inequality.https://jsciences.ut.ac.ir/article_100850_f3baaeae08c1b506e2b87069c404a11a.pdfUniversity of TehranJournal of Sciences, Islamic Republic of Iran1016-110435320240801Evaluating Feature Selection Methods for Macro-Economic Forecasting, Applied for Iran’s Macro-Economic Variables24325610070610.22059/jsciences.2025.383754.1007888ENMahdiGoldaniDepartment of Political Science and Economics, Faculty of Literature and Humanities, Hakim Sabzevari University, Sabzevar, Islamic Republic of IranJournal Article20241014This research examines different feature selection methods to enhance the predictive accuracy of macroeconomic forecasting models, focusing on Iran’s economic indicators derived from World Bank data. Fourteen feature selection techniques were thoroughly compared, classified into Filter, Wrapper, Embedded, and Similarity-based categories. The evaluation utilized Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) metrics under a 10-fold cross-validation scheme. The findings highlight that Stepwise Selection, Tree-based approaches, and Similarity-based methods, especially those employing Hausdorff and Euclidean distances, consistently outperformed others with average MAE values of 32.03 for Stepwise Selection and 62.69 for Hausdorff Distance. Conversely, Recursive Feature Elimination and Variance Thresholding exhibited weaker results, yielding significantly higher average MAE scores. Similarity-based approaches achieved an average rank of 9.125 across datasets, demonstrating their robustness in managing high-dimensional macroeconomic data. These outcomes underscore the value of integrating similarity measures with traditional feature selection techniques to improve the efficiency and reliability of predictive models, offering meaningful insights for researchers and policymakers in economic forecasting.https://jsciences.ut.ac.ir/article_100706_2aae7a14a120874ee4702fa97e37846e.pdfUniversity of TehranJournal of Sciences, Islamic Republic of Iran1016-110435320240801Comparison of Adaptive Neural-Based Fuzzy Inference System and Support Vector Machine Methods for the Jakarta Composite Index Forecasting25726510296110.22059/jsciences.2025.381778.1007882ENAyuMutmainnahDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Hasanuddin University, Makassar, 90245 Indonesia Makassar, IndonesiaSri AstutiThamrinDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Hasanuddin University, Makassar, 90245 Indonesia Makassar, IndonesiaGeorgina MariaTinungkiDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Hasanuddin University, Makassar, 90245 Indonesia Makassar, IndonesiaJournal Article20240902The Jakarta Composite Index (JCI) is a pivotal benchmark for evaluating the performance of all stocks listed on the Indonesia Stock Exchange (IDX). Given the inherent complexity, nonlinearity, and non-stationarity of stock market data, selecting robust forecasting methods is essential. This study compares the performance of the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Support Vector Machine (SVM) in forecasting JCI movements. The researcher assessed prediction accuracy using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The training phase revealed that the optimal ANFIS model employed the generalized bell membership function, outperforming trapezoidal and Gaussian alternatives. Concurrently, the best SVM configuration utilized a linear kernel (cost = 10), demonstrating superior performance compared to radial basis function (RBF) and sigmoid kernels. In the testing phase, ANFIS achieved an RMSE of 39.894 and MAPE of 0.4647, while SVM recorded an RMSE of 38.728 and MAPE of 0.4516. These results underscore the superior predictive capabilities of SVM, positioning it as a reliable tool for stock market forecasting. The study’s findings provide valuable insights for investors and policymakers in navigating market uncertainties and optimizing investment strategies.https://jsciences.ut.ac.ir/article_102961_a7a163a8742de9c9c33f310b067b9b08.pdfUniversity of TehranJournal of Sciences, Islamic Republic of Iran1016-110435320240801Second-ordered Characterization of Generalized Convex Functions and Their Applications in Optimization Problems26727710296210.22059/jsciences.2025.389419.1007912ENMohammad TaghiNadiSchool of Mathematics, Institute for Research in Fundamental Sciences (IPM), P. O. Box 19395-5746, Tehran, Islamic Republic of IranJafarZafarani2 Department of Mathematics, Sheikhbahaee University and University of Isfahan, Isfahan, Islamic Republic of IranJournal Article20250126This survey investigates some developments in<strong> </strong>the second-order characterization of generalized convex functions using the coderivative<strong> </strong>of subdifferential mapping. More precisely, it presents the second-order characterization for quasiconvex, pseudoconvex and invex functions. Furthermore<strong>, </strong>it gives some applications of the second-order subdifferentials in optimization problems such as constrained and unconstrained nonlinear programming.https://jsciences.ut.ac.ir/article_102962_a7ceced9c1c92e505fff3a0c1cb85c54.pdfUniversity of TehranJournal of Sciences, Islamic Republic of Iran1016-110435320240801Abstract102963ENJournal Article20250803https://jsciences.ut.ac.ir/article_102963_69fa6e11324ab6862e9254e7a38201ec.pdfUniversity of TehranJournal of Sciences, Islamic Republic of Iran1016-110435320240801Binder102964ENJournal Article20250803https://jsciences.ut.ac.ir/article_102964_2d7340275322cf3a4b6978467b6ee35b.pdf