检索结果-内蒙古大学图书馆

TESTING FOR DIF IN A MODEL WITH SINGLE PEAKED ITem CHARACTERISTIC CURVES - THE PARELLA MODEL

PSYCHOMETRIKA 1992年第3期57卷 383-397页

作者： HOIJTINK, H MOLENAAR, IW UNIV GRONINGEN DEPT STAT & MEASUREMENT THEORYGROTE KRUISSTRAAT 2-19712 TS GRONINGENNETHERLANDS

The PARELLA model is a probabilistic parallelogram model that can be used for the measurement of latent attitudes or latent preferences. The data analyzed are the dichotomous responses of persons to items, with a one (zero) indicating agreement (disagreement) with the content of the item. The model provides a unidimensional representation of persons and items. The response probabilities are a function of the distance between person and item: the smaller the distance, the larger the probability that a person will agree with the content of the item. This paper discusses how the approach to differential item functioning presented by Thissen, Steinberg, and Wainer can be implemented for the PARELLA model.

关键词： MARGINAL MAXIMUM LIKELIHOOD em-algorithm NONMONOTONE TRACE LINES SINGLE-PEAKED PREFERENCE FUNCTIONS LATENT TRAIT THEORY UNFOLDING DIF DIFFERENTIAL ITem FUNCTIONING

来源：评论

学校读者我要写书评

暂无评论

Data Stream Online Clustering Based on Fuzzy Expectation-Maximization Approach 2

Data Stream Online Clustering Based on Fuzzy Expectation-Max...

引用

2nd IEEE International Conference on Data Stream Mining and Processing (DSMP)

作者： Deineko, Anastasiia O. Zhernova, Polina Ye Gordon, Boris Zayika, Oleksandr O. Pliss, Iryna Pabyrivska, Nelya Kharkiv Natl Univ Radio Elect Artificial Intelligence Dept Kharkov Ukraine Kharkiv Natl Univ Radio Elect Syst Engn Dept Kharkov Ukraine Tallinn Univ Technol Comp Syst Dept Tallinn Estonia Kharkiv Natl Univ Radio Elect Control Syst Res Lab Kharkov Ukraine Lviv Polytech Natl Univ Dept Math Lvov Ukraine

ISBN: (纸本)9781538628744

In the paper the online fuzzy clustering recurrent procedure has been introduced that allows the forming of hyperellipsoidal clusters with an arbitrary orientation of the axes is proposed. Such clustering system is the generalization of a number of known algorithms, it is intended to solve tasks within the general problems of Data Stream Mining (DSM) and Dynamic Data Mining (DDM), when information is sequentially fed to processing in online mode.

关键词： big data dynamic data mining data stream mining computational intelligence em-algorithm fuzzy clustering Kohonen's self-learning soft clustering

来源：评论

学校读者我要写书评

暂无评论

Modeling Fluid Flows in Oil Fields Using the Kalman Filter

引用

Journal of Mathematical Sciences (United States) 2023年第6期272卷 774-782页

作者： Zaikin, A.A. Kareev, I.A. Kazan (Volga region) Federal University Kazan Russian Federation

In this paper, we present a statistical model of the relationship between injection and production wells on an oil field. The model is based on analysis of fluid flows occurring in the oil field;it is a modification of the Kalman filter model. An em-algorithm for estimating the parameters of this model is developed. © 2023, Springer Nature Switzerland AG.

关键词： 62P30 86A04 em-algorithm Kalman filter statistical modeling waterflooding

来源：评论

学校读者我要写书评

暂无评论

Separation of a Mixture of Three-Parameter Lognormal Distributions in the Analysis of Communication Environments

引用

Computational Mathematics and Modeling 2019年第3期30卷 311-319页

作者： Kozlov, V.D. Maysuradze, A.I. Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Moscow Russian Federation

Methods for the separation of a mixture of three-parameter lognormal distributions are investigated theoretically and empirically in the context of modeling message transmission delays in a computer cluster communication environment. Delay modeling based on mixtures of three-parameter lognormal distributions is proposed and parameter estimation methods for such models are investigated. Identifiability of the given family of distributions is proved, which is a necessary condition for the mixture separation problem to be well-posed. The proposed problem-oriented modifications of the standard algorithms are shown to be superior to the traditional methods. © 2019, Springer Science+Business Media, LLC, part of Springer Nature.

关键词： computer cluster communication environment em-algorithm identifiability of a family of distributions message transmission delays point estimation problem-oriented methods separation of a mixture of distributions three-parameter lognormal distribution

来源：评论

学校读者我要写书评

暂无评论

Geometry of Arimoto algorithm

引用

Information Geometry 2020年第2期3卷 183-198页

作者： Toyota, Shoji Graduate School of Mathematics Nagoya University Furo-cho Nagoya 464-8602 Japan

In information theory, the channel capacity, which indicates how efficient a given channel is, plays an important role. The best-used algorithm for evaluating the channel capacity is Arimoto algorithm [3]. This paper aims to reveal an information geometric structure of Arimoto algorithm. In the process of trying to reveal an information geometric structure of Arimoto algorithm, a new algorithm that monotonically increases the Kullback-Leibler divergence is proposed, which is called “the Backward em-algorithm.” Since the Backward em-algorithm is available in many cases where we need to increase the Kullback-Leibler divergence, it has a rich potential for application to many problems of statistics and information theory. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Arimoto algorithm Backword em-algorithm Channel capacity em-algorithm Information geometry

来源：评论

学校读者我要写书评

暂无评论

A hierarchical mixture cure model with unobserved heterogeneity for credit risk

引用

ECONOMETRICS AND STATISTICS 2022年 22卷 39-55页

作者： Dirick, Lore Claeskens, Gerda Vasnev, Andrey Baesens, Bart Katholieke Univ Leuven ORSTAT Naamsestr 69 B-3000 Leuven Belgium Katholieke Univ Leuven Leuven Stat Res Ctr Naamsestr 69 B-3000 Leuven Belgium Univ Sydney Business Sch Abercrombie Bldg H70 Sydney NSW 2006 Australia Katholieke Univ Leuven Fac Econ & Business LIRIS Naamsestr 69 B-3000 Leuven Belgium

The specific nature of credit loan data requires the use of mixture cure models within the class of survival analysis tools. The constructed models allow for competing risks such as early repayment and default, and for incorporating maturity, expressed as an unsusceptible part of the population. A novel further extension of such models incorporates unobserved heterogeneity within the risk groups. A hierarchical expectation-maximization algorithm is derived to fit the models and standard errors are obtained. Simulations and a data analysis illustrate the applicability and benefits of these models, and in particular an improved event time estimation. (c) 2021 EcoSta Econometrics and Statistics. Published by Elsevier B.V. All rights reserved.

关键词： Credit risk modeling Competing risks em-algorithm Mixture cure model Survival analysis Unobserved heterogeneity

来源：评论

学校读者我要写书评

暂无评论

Improved Clustering Using Nice Initialization

Improved Clustering Using Nice Initialization

引用

IEEE Conference on Global Communications (IEEE GLOBECOM) - Intelligent Communications for Shared Prosperity

作者： Huang, Huyunting Tang, Ziyang Zhang, Tonglin Yang, Baijian Purdue Univ W Lafayette IN 47907 USA

ISBN: (纸本)9798350310900

Popular clustering methods, such as the k-means and the Gaussian mixture model (GMM), are composed of an initialization stage and an iteration stage. Although this is well known, the role of the two stages has not been well studied for existing clustering methods yet. To understand this issue, the current research investigates well-known existing k-means and the GMM methods. The finding is that the initialization stage is more critical than the iteration stage. Based on this issue, the research develops improved k-means and GMM methods by using a nice initialization, which significantly enhances the performance of the corresponding methods. Experiments based on Monte Carlo simulations show that the proposed improved k-means and GMM methods can completely identify the true clusters if they are well separated from each, but this cannot be achieved by the existing k-means and GMM methods. Experiments based on a real-world dataset show that the proposed methods can be efficiently combined with dimension-reduction techniques for clustering high-dimensional massive data.

关键词： adjusted rand index em-algorithm Gaussian mixture model k-means

来源：评论

学校读者我要写书评

暂无评论

Modeling and Self-Similarity Analysis of Non-Poissonian Traffic Represented by Multimodal Non-Typical Pascal and Rice Distributions

Modeling and Self-Similarity Analysis of Non-Poissonian Traf...

引用

Systems of Signals Generating and Processing in the Field of on Board Communications Conference

作者： Faizullin, R. R. Yaushev, S. T. Insarov, A. Y. Kazan Natl Res Tech Univ Kazan Russia

ISBN: (纸本)9781728106069

Modern stage of development of information and communication networks requires solving of crucial tasks of network traffic statistical analysis and traffic simulation modeling. The predominance of non-Poisson traffic leads to the impossibility of analyzing multichannel communication systems by the methods of queuing theory that used to describe telephone networks. The last decade has paid much attention to research on traffic that has signs of self-similarity. The main purpose of this work is a statistical analysis of non-Poissonian traffic, represented by multimodal non-standard Pascal (negative binomial) and Rice distributions. As a result, a study of the self-similarity degree has been performed by the R/S analysis and the aggregation method. In addition, we propose to use em-algorithm with an algorithm for determining an optimal number of clusters for an approximation of non-typical multimodal distributions.

关键词： self-similar traffic Rice distribution Pascal distribution em-algorithm QoS

来源：评论

学校读者我要写书评

暂无评论

A Parametric Mixture Model of Three Different Distributions: An Approach to Analyse Heterogeneous Survival Data

A Parametric Mixture Model of Three Different Distributions:...

引用

21st National Symposium on Mathematical Sciences (SKSM)

作者： Mohammed, Yusuf Abbakar Yatim, Bidin Ismail, Suzilah Univ Utara Malaysia Coll Arts & Sci Sch Quantitat Sci Kedah Malaysia

ISBN: (纸本)9780735412415

A parametric mixture model of three different distributions is proposed to analyse heterogeneous survival data. The maximum likelihood estimators of the postulated parametric mixture model are estimated by applying an Expectation Maximization algorithm (em) scheme. The simulations are performed by generating data, sampled from a population of three component parametric mixture of three different distributions. The parameters estimated by the proposed em algorithm scheme are close to the parameters of the postulated model. To investigate the consistency and stability of the em scheme, the simulations are repeated several times. The repetitions of the simulation gave parameters closer to the values of postulated models, with relatively small standard errors. Log likelihood, AIC and BIC are computed to compare the proposed mixture model with parametric mixture models of one distribution. The calculated values of Log likelihood, AIC and BIC are all in favour of the proposed parametric mixture model of different distributions.

关键词： Survival time analysis Maximum likelihood em-algorithm mixture model simulation Exponential distribution Gamma Distribution Weibull Distribution

来源：评论

学校读者我要写书评

暂无评论

Estimating Parameter for the Mixture Generalized Gamma Distribution 18

Estimating Parameter for the Mixture Generalized Gamma Distr...

引用

10th International Conference on Computer Modeling and Simulation (ICCMS)

作者： Phaphan, Wikanda King Mongkuts Univ Technol North Bangkok Fac Sci Appl Dept Appl Stat Bangkok Thailand

ISBN: (纸本)9781450363396

Mixture generalized gamma distribution is a combination of two distributions -- Generalized gamma distribution and length biased generalized gamma distribution. This distribution is presented by Suksaengrakcharoen and Bodhisuwan in 2014. The fmdings showed that probability density function (pdf) had fairly complexities, so it made problems in estimating parameters. The problem occurred in parameter estimation was that we were unable to calculate estimators in the form of critical expression. Thus, we will use numerical estimation to find the estimators. In this study, we presented a new method of the parameter estimation by using the expectation maximization algorithm (em), the conjugate gradient method, and the quasi -Newton method. The data was generated by acceptance -rejection method which is used for estimating alpha, beta, lambda and p . lambda is the scale parameter, p is the weight parameter, alpha and beta are the shape parameters. We will use Monte Carlo technique to fmd the estimator's performance. Determining the size of sample equals 30, 100 and the simulation were repeated 20 times in each case. We evaluated the effectiveness of the estimators which was introduced by considering values of the mean squared errors and the bias. The findings revealed that the em -algorithm had proximity to the actual values determined. Also, the maximum likelihood estimators via the conjugate gradient and the quasi Newton method are less precision than the maximum likelihood estimators via the em -algorithm.

关键词： Conjugate gradient method quasi-Newton method em-algorithm generalized gamma distribution length biased generalized gamma distribution maximum likelihood method

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：