检索结果-内蒙古大学图书馆

cluster sampling: consequences of data analysis on drawing conclusions

REVUE D EPIDEMIOLOGIE ET DE SANTE PUBLIQUE 2005年第1期53卷 43-50页

作者： Laurent, C Etard, JF Univ Montpellier Inst Rech Dev UMR 145 F-34394 Montpellier 5 France

Background: cluster sampling is commonly used since it does not require a sampling frame which lists all the individual enumeration units. However, this sampling design is often less precise than simple random sampling due to frequent homogeneity of individuals within clusters. This note illustrates that the precision of parameters such as mean, prevalence and odds ratio can, be biased when the data analysis ignores the sampling design, yielding to possibly erroneous conclusions. Methods: Data from a cluster sampling among clandestine sex workers in Senegal were used. Two analyses were performed and their results were compared. The first analysis took into account the sampling design (design-based analysis) while the second did not (naive analysis). Results: The range of confidence intervals in design-based analysis differed from 43% to +84% with regard to those of naive analysis, and different conclusions could be drawn. For instance, the human immunodeficiency virus (HIV) infection in clandestine sex workers was associated with condoms use and perceived risk of HIV infection in design-based analysis but not in naive analysis. Conclusion: The data analysis must take into account the sampling design, and this is facilitated by the availability of statistical software with survey analysis capabilities.

关键词： cluster sampling complex sampling design effect data analysis

来源：评论

学校读者我要写书评

暂无评论

Layered Graph Matching with Composite cluster sampling

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2010年第8期32卷 1426-1442页

作者： Lin, Liang Liu, Xiaobai Zhu, Song-Chun Sun Yat Sen Univ Sch Software Guangzhou Higher Educ Mega Ctr Guangzhou 51000 Peoples R China Lotus Hill Res Inst Comp Vis & Informat Sci Ezhou 436000 Hubei Peoples R China Univ Calif Los Angeles Dept Stat Los Angeles CA 90095 USA

This paper presents a framework of layered graph matching for integrating graph partition and matching. The objective is to find an unknown number of corresponding graph structures in two images. We extract discriminative local primitives from both images and construct a candidacy graph whose vertices are matching candidates (i.e., a pair of primitives) and whose edges are either negative for mutual exclusion or positive for mutual consistence. Then we pose layered graph matching as a multicoloring problem on the candidacy graph and solve it using a composite cluster sampling algorithm. This algorithm assigns some vertices into a number of colors, each being a matched layer, and turns off all the remaining candidates. The algorithm iterates two steps: 1) sampling the positive and negative edges probabilistically to form a composite cluster, which consists of a few mutually conflicting connected components (CCPs) in different colors and 2) assigning new colors to these CCPs with consistence and exclusion relations maintained, and the assignments are accepted by the Markov Chain Monte Carlo (MCMC) mechanism to preserve detailed balance. This framework demonstrates state-of-the-art performance on several applications, such as multi-object matching with large motion, shape matching and retrieval, and object localization in cluttered background.

关键词： Graph matching graph partitioning DDMCMC cluster sampling

来源：评论

学校读者我要写书评

暂无评论

Generating and validating cluster sampling matrices for model-free factor screening

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2024年第1期313卷 241-257页

作者： Shi, Wen Chen, Ao Xie, Xiang Cent South Univ Business Sch Changsha 410083 Peoples R China

Morris' elementary effect-based screening (MM) has been widely used in a variety of domains to identify a few important factors among many possible ones. In MM, cluster sampling offers substantial computational savings over non-cluster sampling, but it remains a challenge to construct a cluster sampling matrix that generates any particular number of elementary effects for each factor. In this paper, we thoroughly address this issue. We uncover the mathematical association between distinct block sampling matrices within the complete cluster sampling matrix, by introducing a "dummy" sub-block matrix. By leveraging this property, we propose an easy-to-implement adaptive cluster sampling (ACS) method that is capable of identifying the appropriate sub-block sampling matrix to use. Its advantage over existing brute-force methods is that it can provide easy-to-obtain cluster sampling matrices, and it can be applied to computational model with any number of factors given a prior. We demonstrate the attractive properties of ACS using analytical proofs and simulation experiments. We show the robustness of ACS via a real-world case study. Our code for the algorithm is available online. (c) 2023 Elsevier B.V. All rights reserved.

关键词： Simulation Factor screening cluster sampling Elementary effect method Simulation experiments

来源：评论

学校读者我要写书评

暂无评论

MLRMPA: An R package of multiple linear regression model population analysis based on a cluster sampling technique for variable selection of high dimensional data

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2014年 132卷 124-132页

作者： Xie, Meihong Deng, Fangfang Zhang, Xiaoyun Tian, Yueli Li, Peizhen Zhai, Honglin Lanzhou Univ Coll Chem & Chem Engn Lanzhou 730000 Gansu Peoples R China

We develop an R package MLRMPA for fitting a pool of models between response variable and chemical descriptors. It is an embedded method combining feature selection with model building. The feature selection procedure is a cluster sampling method and different from model population analysis (MPA) that was implemented in a previously published study. The modeling process performs multiple stepwise regression analysis using the sampled features from the clustered group. This paper provides the algorithm and method implemented in the R package, which includes VarCor feature selection, cluster sampling, model building and model checking. This package is applied to establish an optimal linear model to predict the response and detect outliers from suboptimal models. (c) 2014 Elsevier B.V. All rights reserved.

关键词： Feature selection cluster sampling Multiple linear regression model population analysis R package

来源：评论

学校读者我要写书评

暂无评论

FedCSR: A new cluster sampling based on rotation mechanism in horizontal federated learning?

引用

COMPUTER COMMUNICATIONS 2023年 210卷 312-320页

作者： Dai, Qiang Yan, Tongjiang Ren, Pengcheng China Univ Petr Qingdao 266580 Peoples R China

Horizontal federated learning (HFL) is a distributed framework that can be used when datasets from various participants have similar feature spaces but different sample spaces. HFL employs clustering algorithms to facilitate information sharing among cluster clients and model aggregation. However, this approach is not suitable for data with heterogeneity, and its stability cannot be guaranteed. Differing from all the current methods to address these issues, we propose a new HFL framework by employing a cluster sampling method based on a rotation mechanism. In our method, we calculate the magnitude of differences in client data by using Gaussian Model Mixture (GMM), and adaptively adjust the probability of intra-cluster clients being selected by the server as well as the number of clusters. Our numerical experiments show that the new framework can handle different data scenarios and outperforms other baselines in terms of convergence speed and accuracy.

关键词： Federated learning cluster sampling Heterogeneity

来源：评论

学校读者我要写书评

暂无评论

An I/O Efficient Distributed Approximation Framework Using cluster sampling

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2019年第7期30卷 1494-1511页

作者： Zhang, Xuhong Wang, Jun Ji, Shouling Yin, Jiangling Wang, Rui Zhou, Xiaobo Jiang, Changjun Univ Cent Florida Dept Elect & Comp Engn Orlando FL 32816 USA Zhejiang Univ Inst Cyberspace Res Coll Comp Sci & Technol Hangzhou 310027 Zhejiang Peoples R China Alibaba ZJU Joint Res Inst Frontier Technol Hangzhou 310027 Zhejiang Peoples R China Univ Colorado Dept Comp Sci Colorado Springs CO 80918 USA Tongji Univ Key Lab Embedded Syst & Serv Comp Shanghai 200000 Peoples R China

In this paper, we present an I/O efficient distributed approximation framework to support approximations on arbitrary sub-datasets of a large dataset. Due to the prohibitive storage overhead of caching offline samples for each sub-dataset, existing offline sample-based systems provide high accuracy results for only a limited number of sub-datasets, such as the popular ones. On the other hand, current online sample-based approximation systems, which generate samples at runtime, do not take into account the uneven storage distribution of a sub-dataset. They work well for uniform distribution of a sub-dataset while suffer low I/O efficiency and poor estimation accuracy on unevenly distributed sub-datasets. To address the problem, we develop a distribution aware method called CLAP (cluster sampling based approximation). Our idea is to collect the occurrences of a sub-dataset at each logical partition of a dataset (storage distribution) in the distributed system, and make good use of such information to enable I/O efficient online sampling. There are three thrusts in CLAP. First, we develop a probabilistic map to reduce the exponential number of recorded sub-datasets to a linear one. Second, we apply the cluster sampling with unequal probability theory to implement a distribution-aware method for efficient online sampling for a single or multiple sub-datasets. Third, we enrich CLAP support with more complex approximations such as ratio and regression using bootstrap based estimation beyond the simple aggragation approxiamtions. Forth, we add an option in CLAP to allow users specifying a target error bound when submitting an approximation job. Fifth, we quantitatively derive the optimal sampling unit size in a distributed file system by associating it with approximation costs and accuracy. We have implemented CLAP into Hadoop as an example system and open sourced it on GitHub. Our comprehensive experimental results show that CLAP can achieve a speedup by up to 20 x over t

关键词： Approximation cluster sampling sub-dataset storage distribution Hadoop

来源：评论

学校读者我要写书评

暂无评论

A review of adaptive cluster sampling: 1990-2003

引用

ENVIRONMENTAL AND ECOLOGICAL STATISTICS 2005年第1期12卷 55-94页

作者： Turk, P Borkowski, JJ Montana State Univ Dept Math Sci Bozeman MT 59717 USA

Adaptive cluster sampling (ACS) is an adaptive sampling scheme which operates under the rule that when the observed value of an initially selected sampling unit satisfies some condition of interest, C, other additional units in some pre-defined accompanying neighborhood are also added to the sample. In turn, if any of these additional units satisfy C, then their corresponding unit neighborhoods are added to the sample as well, and so on. This process stops when no additional units satisfying C are encountered. This paper will provide a review of the major developments and issues in ACS since its introduction by Thompson (1990) [Journal of the American Statistical Association, 85, 1050-1059]. (c) 2005 Springer Science + Business Media, Inc.

关键词： bootstrapping cluster sampling detectability double sampling Rao-Blackwell estimator stratified sampling

来源：评论

学校读者我要写书评

暂无评论

General Estimation Procedures for Population Mean in Successive cluster sampling in Presence of Scrambled Response Situation

引用

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES INDIA SECTION A-PHYSICAL SCIENCES 2023年第1期93卷 95-105页

作者： Nazrin, Chowdhury Sadeka Bandyapadhya, Arnab Gupta, Arindam Univ Burdwan Dept Stat Burdwan W Bengal India Asansol Engn Coll Dept Math Asansol W Bengal India

We have addressed the problems of estimation in successive cluster sampling in the presence of scrambled response situation. A generalized class of estimators for population mean in two-occasion successive sampling under two-stage cluster sampling schemes has been suggested. Numerous estimators have been shown as a member of the recommended family. We have derived the properties of the proposed strategy and also found its optimum condition. The superiority of the suggested strategy over the conventional ones has been demonstrated through empirical investigation carried over the data set of real as well as simulated population studies. Relevance of Our Work in Broad Context In practical surveys, often it may be seen that a complete list of all the items of study in the population is not available which indicates that drawing a simple random sample is not possible in such cases. For instance, in socioeconomic survey, a list of households is not generally available, whereas a list of residential houses each accommodating a number of households should be available with municipal and other appropriate authorities. In such cases, it may be advisable to draw a simple random sample of houses and survey all the households belonging to sample households. This procedure is known as cluster sampling. It is also a common experience in sample surveys on sensitive data that someone is agreed to response but prefers to hide the true value for avoiding possible social stigma and harassment. These people prefer to hide their true responses. Therefore, the available sample of returns is camouflaged. It is noted that the most of recently developed estimation procedures of successive sampling are based on simple random sampling only and no attempt has been taken for estimation of population parameters in successive sampling under cluster sampling scheme. It is also observed that no significant step has been taken yet to estimate population parameters under cluster sampling in the presen

关键词： Successive sampling cluster sampling Scrambled response Auxiliary variable Mean square error

来源：评论

学校读者我要写书评

暂无评论

COMPARISON OF THE PERFORMANCE OF LINE sampling TO OTHER FORMS OF cluster sampling

引用

FOREST ECOLOGY AND MANAGEMENT 1994年第2-3期68卷 365-373页

作者： KLEINN, C Abteilung für Forstliche Biometrie Universität Freiburg Werderring 6 D-79085 Freiburg Germany

Line sampling is a widely applied method in field surveys to assess spatially distributed variables. The values of the variable of interest are recorded along line-shaped survey elements. Line sampling can be viewed as a special case of cluster sampling with fixed cluster form where the number of elements in the cluster is large and the distance between the elements small. In this study the precision of estimators for the following survey elements is examined: line segment, L-shape, cross, circle, square and equilateral triangle, i.e. we estimate lines of limited length c (in contrast to transects which cross the entire survey region). The precision of a line sample depends on the probability density function (PDF) of interpoint distances on the line. The PDFs are given for the six survey elements listed above. In an example with a simple covariance function cov(d)=e(-d) the variance for given line length c increases in the order: line segment, L-shape, circle, square, cross, equilateral triangle. A comparison of line sampling and cluster sampling with the same form and size of survey element shows that, except for the circle, clusters of only a few cluster points give more precise results than line sampling when small survey elements are used, assuming the given covariance function is correct.

关键词： LINE sampling cluster sampling STATISTICAL PRECISION

来源：评论

学校读者我要写书评

暂无评论

On a version of cluster sampling and its practical use

引用

JOURNAL OF STATISTICAL PLANNING AND INFERENCE 2003年第1期113卷 25-34页

作者： Chaudhuri, A Pal, S Indian Stat Inst Appl Stat Unit Kolkata 700035 W Bengal India Govt W Bengal River Res Inst Kolkata 700014 W Bengal India

We consider a practical sample survey problem in which we require to reach households in villages which in batches are served by certain primary health centres (PHC) or by somewhat 'bigger' primary health centres (BPHC) located in various territorial cross-sections in a district near Calcutta. We present here a comparative study of alternative schemes of sampling the PHC's and the BPHC's and estimating the totals of variate - values related to all the BPHC's and PHC's in the district. The situation demands adequate representation of the BPHC's in the sample and geographically, each BPHC separately has an exclusive group of PHC's contiguous and hence attached to it. So, a BPHC together with the neighbouring PHC's may be supposed to constitute a cluster, each cluster disjoint with every other and values within a cluster are supposed to be well and positively correlated. Some of the possible alternative ways of sampling are: (1) sampling from the pool of all the BPHC's and PHC's taken together, (2) sampling independently from the two separate strata of BPHC's and PHC's and (3) Two-stage sampling with the clusters mentioned above as the first stage units and choosing from each selected cluster the BPHC in it and a sample from the PHC's contiguous to this BPHC. But we recommend a fourth alternative that selects first a sample of PHC's from all the PHC's in a cross-section and attaches to each selected PHC the BPHC in the cluster to which it belongs. This yields several alternative estimators of interest. By a simulation exercise, we present numerical findings of relative performances of these various procedures. Though it is difficult to identify a best procedure theoretically, empirically our proposed procedure appears to be quite encouraging. It ensures a desirably wide territorial coverage of PHC's in the sample and reducing a stage of sampling promises to yield efficient estimators. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： cluster sampling simulation stratified sampling two-stage sampling

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：