检索结果-内蒙古大学图书馆

Parameter estimation from incomplete data in binomial regression when the missing data mechanism is nonignorable

BIOMETRICS 1996年第3期52卷 1071-1078页

作者： Ibrahim, JG Lipsitz, SR DANA FARBER CANC INST DIV BIOSTATBOSTONMA 02115

We propose a method for estimating parameters in binomial regression models when the response variable is missing and the missing data mechanism is nonignorable. We assume throughout that the covariates are fully observed. Using a legit model for the missing data mechanism, we show how parameter estimation can be accomplished using the em algorithm by the method of weights proposed in Ibrahim (1990, Journal of the American Statistical Association 85, 765-769). An example from the Six Cities Study (Ware et al., 1984, American Review of Respiratory Diseases 129, 366-374) is presented to illustrate the method.

关键词： em-algorithm generalized linear models nonignorable missing data

来源：评论

学校读者我要写书评

暂无评论

Influence Diagnostics for a Skew Extension of the Grubbs Measurement Error Model

引用

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION 2009年第4期38卷 667-681页

作者： Montenegro, Lourdes C. Bolfarine, Heleno Lachos, Victor H. Univ Fed Minas Gerais Dept Estat Ast Belo Horizonte MG Brazil Univ Sao Paulo Dept Estat Ast Sao Paulo Brazil Univ Estadual Campinas Dept Estat Ast Sao Paulo Brazil

Influence diagnostics methods are extended in this article to the Grubbs model when the unknown quantity x (latent variable) follows a skew-normal distribution. Diagnostic measures are derived from the case-deletion approach and the local influence approach under several perturbation schemes. The observed information matrix to the postulated model and Delta matrices to the corresponding perturbed models are derived. Results obtained for one real data set are reported, illustrating the usefulness of the proposed methodology.

关键词： em-algorithm Grubbs model Local influence Skew-normal

来源：评论

学校读者我要写书评

暂无评论

Applications of Bigdata Technologies in the Comparison of BMTD and ARIMA Models for the Prediction of Internet Congestion

引用

IEEE ACCESS 2024年 12卷 56642-56651页

作者： Hassan, Mohamed Yusuf United Arab Emirates Univ Dept Stat Al Ain U Arab Emirates

The pace in the development and adoption of the new technologies for bigdata analytics has changed dramatically over the last several decades, and the amount of data being digitally ingested and stored is expanding exponentially and rapidly. These data include structured, semi-structured and unstructured, and come in different sizes and formats. To utilize these vast resources, the knowledge and the skills needed to manage and to convert it into information is crucial. In this paper, firstly, the commonly used technologies, platforms, computational tools and the techniques currently in use for the ingesting, processing, storing and analyzing bigdata are reviewed. Secondly, those technologies are utilized to predict internet congestion by employing the bivariate mixture transition distribution (BMTD), expectation-maximization (em) algorithm and the autoregressive integrated moving average (ARIMA) models. BMTD models are very effective in capturing non-Gaussian and nonlinear features, such as bursts of activity and outliers, in a single unified model class. These models do not assume equally spaced, as well as independence, which are the key weaknesses of some other available time series and marked point processes models. Both the Weibull BMTD and the ARIMA models are very effective time series predictive models, but the comparison of their predictive performances is not yet addressed in the statistics and the machine learning literature.

关键词： Marked point processes Hadoop Sparklyr Sqoop em-algorithm ARIMA parquet

来源：评论

学校读者我要写书评

暂无评论

A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition

引用

SPEECH COMMUNICATION 1998年第4期24卷 299-323页

作者： Deng, L Univ Waterloo Dept Elect & Comp Engn Waterloo ON N2L G1 Canada

An overview of a statistical paradigm for speech recognition is given where phonetic and phonological knowledge sources, drawn from the current understanding of the global characteristics of human speech communication, are seamlessly integrated into the structure of a stochastic model of speech. A consistent statistical formalism is presented in which the submodels for the discrete, feature-based phonological process and the continuous, dynamic phonetic process in human speech production are computationally interfaced. This interface enables global optimization of a parsimonious set of model parameters that accurately characterize the symbolic, dynamic, and static components in speech production and explicitly separates distinct sources of the speech variability observable at the acoustic level. The formalism is founded on a rigorous mathematical basis, encompassing computational phonology, Bayesian analysis and statistical estimation theory, nonstationary time series and dynamic system theory, and nonlinear function approximation (neural network) theory. Two principal ways of implementing the speech model and recognizer are presented, one based on the trended hidden Markov model (HMM) or explicitly defined trajectory model, and the other on the state-space or recursively defined trajectory model. Both implementations build into their respective recognition and model-training algorithms a continuity constraint on the internal, production-affiliate trajectories across feature-defined phonological units. The continuity and the parameterized structure in the dynamic speech model permit a joint characterization of the contextual and speaking-style variations manifested in speech acoustics, thereby holding promises to overcome some key limitations of the current speech recognition technology (C) 1998 Elsevier Science B.V. All rights reserved.

关键词： speech dynamic recognition features em-algorithm task variables continuity constraint

来源：评论

学校读者我要写书评

暂无评论

Some simulation/computation in multivariate linear models of scale mixtures of skew-normal-Cauchy distributions

引用

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION 2022年第11期51卷 6425-6440页

作者： Kahrari, Fereshte Arellano-Valle, Reinaldo Boris da Silva Ferreira, Clecio Gallardo, Diego Shahid Chamran Univ Ahvaz Dept Stat Ahvaz Iran Pontificia Univ Catolica Chile Dept Estadist Santiago Chile Univ Fed Juiz de Fora Dept Stat Juiz De Fora Brazil Univ Atacama Chile Dept Estadist Copiapo Chile

In this work, we extend standard likelihood-based procedures to the multivariate linear model using the scale mixtures of multivariate skew-normal-Cauchy distributions. A simple em algorithm for iteratively computing maximum likelihood estimates is derived. The observed information matrix is computed analytically to account for standard errors. Some results are obtained from real and simulated datasets to illustrate the usefulness of the proposed model.

关键词： em-algorithm Multivariate linear regression models Scale mixtures skew-normal-Cauchy distributions Shape mixture

来源：评论

学校读者我要写书评

暂无评论

Mixture Normal Models in which the Proportions of Susceptibility are Related to Dose Levels

引用

Acta Mathematicae Applicatae Sinica 2010年第3期26卷 463-472页

作者： Bing He Min Chen Li-xin Song De-hui Wang College of Mathematics Jilin University Changchun Jilin 130012 China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China Department of Mathematics Dalian University of Technology Dalian 116024 China

A problem that frequently occurs in biological experiments with laboratory animals is that some subjects are less susceptible to the treatment group than others. Finite mixture models have traditionally been used to describe the distribution of responses in treated subjects for such studies. In this paper, we first study the mixture normal model with multi-levels and multiple mixture sub-populations under each level, with particular attention being given to the model in which the proportions of susceptibility are related to dose levels, then we use em-algorithm to find the maximum likelihood estimators of model parameters. Our results are generalizations of the existing results. Finally, we illustrate realistic significance of the above extension based on a set of real dose-response data.

关键词： Dose-response em-algorithm mixture normal models susceptibility

来源：评论

学校读者我要写书评

暂无评论

Improving image segmentation by using energy function based on mixture of Gaussian pre-processing

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2016年 41卷 239-246页

作者： Vakili, Nima Rezghi, Mansoor Hosseini, S. Mohammad Univ Tarbiat Modares Dept Appl Math POB 14115-175 Tehran Iran Univ Tarbiat Modares Dept Comp Sci POB 14115-175 Tehran Iran

In this paper, by proposing a two-stage segmentation method based on active contour model, we improve the procedure of former image segmentation methods. The first stage of our method is computing weights, means and variances of image by utilizing Mixture of Gaussian distribution which parameters are obtained from em-algorithm. Once they are obtained, in the second stage, by incorporating level set method for minimizing energy function, the segmentation is achieved. We use an adaptive direction function to make the curve evolution robust against the curves initial position and a nonlinear adaptive velocity to speed up the process of curve evolution and also a probability-weighted edge and region indicator function to implement a robust segmentation for objects with weak boundaries. The paper consists of minimizing a functional containing a penalty term in an attempt to maintain the signed distance property in the entire domain and an external energy term such that it achieves a minimum when the zero level set of the function is located at desired position. (C) 2016 Elsevier Inc. All rights reserved.

关键词： Active contour Image segmentation Level set Gaussian mixture distribution em-algorithm Pre-processing

来源：评论

学校读者我要写书评

暂无评论

Generalized inverse-Gaussian frailty models with application to TARGET neuroblastoma data

引用

ANNALS OF THE INSTITUTE OF STATISTICAL MATHemATICS 2021年第5期73卷 979-1010页

作者： Piancastelli, Luiza S. C. Barreto-Souza, Wagner Mayrink, Vinicius D. Univ Coll Dublin Sch Math & Stat Dublin D04 V1W8 4 Ireland King Abdullah Univ Sci & Technol Stat Program Thuwal 239556900 Saudi Arabia Univ Fed Minas Gerais Dept Estat BR-31270901 Belo Horizonte MG Brazil

A new class of survival frailty models based on the generalized inverse-Gaussian (GIG) distributions is proposed. We show that the GIG frailty models are flexible and mathematically convenient like the popular gamma frailty model. A piecewise-exponential baseline hazard function is employed, yielding flexibility for the proposed class. Although a closed-form observed log-likelihood function is available, simulation studies show that employing an em-algorithm is advantageous concerning the direct maximization of this function. Further simulated results address the comparison of different methods for obtaining standard errors of the estimates and confidence intervals for the parameters. Additionally, the finite-sample behavior of the em-estimators is investigated and the performance of the GIG models under misspecification assessed. We apply our methodology to a TARGET (Therapeutically Applicable Research to Generate Effective Treatments) data about the survival time of patients with neuroblastoma cancer and show some advantages of the GIG frailties over existing models in the literature.

关键词： em-algorithm Frailty Generalized inverse-Gaussian models Neuroblastoma Robustness

来源：评论

学校读者我要写书评

暂无评论

The Skew-Reflected-Gompertz distribution for analyzing symmetric and asymmetric data

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHemATICS 2019年 349卷 132-141页

作者： Hoseinzadeh, Akram Maleki, Mohsen Khodadadi, Zahra Contreras-Reyes, Javier E. Azad Univ Marvdasht Branch Dept Stat Marvdasht Iran Shiraz Univ Dept Stat Coll Sci Shiraz Iran Univ Valparaiso Inst Estadist Valparaiso Chile

In this work, we have defined a new family of skew distribution: the Skew-Reflected-Gompertz. We have also derived some of its probabilistic and inferential properties. The maximum likelihood estimates of the proposed distribution parameters are obtained via an em-algorithm, and performances of the proposed model and its estimates are shown via simulation studies as well as real applications. Three real datasets are also used to illustrate the model performance which can compete against some well-known skew distributions frequently used in applications. (C) 2018 Elsevier B.V. All rights reserved.

关键词： em-algorithm Finite mixtures Maximum likelihood estimates Skew-reflected-Gompertz distribution Two-piece distributions

来源：评论

学校读者我要写书评

暂无评论

Phase term modeling for enhanced feature-space VTS

引用

SPEECH COMMUNICATION 2017年 89卷 84-91页

作者： Korenevsky, Maxim ITMO Univ St Petersburg Russia Speech Technol Ctr St Petersburg Russia

This paper proposes a generalization of the Vector Taylor Series (VTS) approach for the compensation of speech feature distortions. It uses a phase term aware representation of the speech distortion model. It considers this term as a Gaussian random vector with unknown parameters in the same manner as it is conventionally done for additive noise. These parameters are estimated by means of the em-algorithm. The explicit expressions for parameters update are derived. The minimum mean square error (MMSE) estimate of clean speech features is also obtained. Experiments carried out on the Aurora2 and Aurora4 databases show that the proposed approach outperforms the phase-insensitive version of feature-space VTS significantly for both GMM and DNN acoustic models. It is also shown that the combination of the proposed approach with the cepstral mean normalization (CMN) provides additional accuracy gains. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Robust speech recognition Vector Taylor Series (VTS) Feature compensation Phase term modeling em-algorithm MMSE estimate Aurora2 Aurora4 Cepstral mean and variance normalization (CMVN)

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：