Jump to Main Content
PubAg
Main content area
Search
« Previous 
1  50 of 123

Next »
Search Results
 Author:
 Bergé, Laurent R.; Bouveyron, Charles; Corneli, Marco; Latouche, Pierre
 Source:
 Computational statistics & data analysis 2019 v.137 pp. 247270
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; Show all 3 Subjects
 Abstract:
 ... Textual interaction data involving two disjoint sets of individuals/objects are considered. An example of such data is given by the reviews on web platforms (e.g. Amazon, TripAdvisor, etc.) where buyers comment on products/services they bought. A new generative model, the latent topic block model (LTBM), is developed along with an inference algorithm to simultaneously partition the elements of eac ...
 DOI:
 10.1016/j.csda.2019.03.005

https://dx.doi.org/10.1016/j.csda.2019.03.005
 Author:
 Chaudhuri, Arin; Hu, Wenhao
 Source:
 Computational statistics & data analysis 2019 v.135 pp. 1524
 ISSN:
 01679473
 Subject:
 algorithms, etc ; covariance; data collection; Show all 3 Subjects
 Abstract:
 ... Classical dependence measures such as Pearson correlation, Spearman’s ρ, and Kendall’s τ can detect only monotonic or linear dependence. To overcome these limitations, Székely et al. proposed distance covariance and its derived correlation. The distance covariance is a weighted L2 distance between the joint characteristic function and the product of marginal distributions; it is 0 if and only if t ...
 DOI:
 10.1016/j.csda.2019.01.016

https://dx.doi.org/10.1016/j.csda.2019.01.016
 Author:
 Marbac, Matthieu; Vandewalle, Vincent
 Source:
 Computational statistics & data analysis 2019 v.132 pp. 167179
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; Show all 3 Subjects
 Abstract:
 ... In the framework of modelbased clustering, a model allowing several latent class variables is proposed. This model assumes that the distribution of the observed data can be factorized into several independent blocks of variables. Each block is assumed to follow a latent class model (i.e., mixture with conditional independence assumption). The proposed model includes variable selection, as a speci ...
 DOI:
 10.1016/j.csda.2018.06.013

https://dx.doi.org/10.1016/j.csda.2018.06.013
 Author:
 Wei, Yuhong; Tang, Yang; McNicholas, Paul D.
 Source:
 Computational statistics & data analysis 2019 v.130 pp. 1841
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; Show all 3 Subjects
 Abstract:
 ... Robust clustering from incomplete data is an important topic because, in many practical situations, real datasets are heavytailed, asymmetric, and/or have arbitrary patterns of missing observations. Flexible methods and algorithms for modelbased clustering are presented via mixture of the generalized hyperbolic distributions and its limiting case, the mixture of multivariate skewt distributions ...
 DOI:
 10.1016/j.csda.2018.08.016

https://dx.doi.org/10.1016/j.csda.2018.08.016
 Author:
 Jhong, JaeHwan; Koo, JaYong
 Source:
 Computational statistics & data analysis 2019 v.133 pp. 228244
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; regression analysis; Show all 3 Subjects
 Abstract:
 ... We consider the problem of simultaneously estimating a finite number of quantile functions with Bsplines and the total variation penalty. For the implementation of simultaneous quantile function estimators, we develop a new coordinate descent algorithm taking into account a special structure of the total variation penalty determined by Bspline coefficients. The entire paths of solution paths for ...
 DOI:
 10.1016/j.csda.2018.10.005

https://dx.doi.org/10.1016/j.csda.2018.10.005
 Author:
 Manghi, Roberto F.; Cysneiros, Francisco José A.; Paula, Gilberto A.
 Source:
 Computational statistics & data analysis 2019 v.129 pp. 4760
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; diagnostic techniques; linear models; Show all 4 Subjects
 Abstract:
 ... Statistical procedures are proposed in generalized additive partial linear models (GAPLM) for analyzing correlated data. A reweighed iterative process based on the backfitting algorithm is derived for the parameter estimation from a penalized GEE. Discussions on the inferential aspects of GAPLM, particularly on the asymptotic properties of the former estimators as well as on the effective degrees ...
 DOI:
 10.1016/j.csda.2018.08.005

https://dx.doi.org/10.1016/j.csda.2018.08.005
 Author:
 Banerjee, Sayantan; Akbani, Rehan; Baladandayuthapani, Veerabhadran
 Source:
 Computational statistics & data analysis 2019 v.132 pp. 4669
 ISSN:
 01679473
 Subject:
 algorithms, etc ; Bayesian theory; data collection; geometry; graphs; models; neoplasms; proteomics; Show all 8 Subjects
 Abstract:
 ... Clustering methods for multivariate data exploiting the underlying geometry of the graphical structure between variables are presented. As opposed to standard approaches for graph clustering that assume known graph structures, the edge structure of the unknown graph is first estimated using sparse regression based approaches for sparse graph structure learning. Subsequently, graph clustering on th ...
 DOI:
 10.1016/j.csda.2018.08.009

https://dx.doi.org/10.1016/j.csda.2018.08.009
 Author:
 Hsu, HsiangLing; Chang, Yuanchin Ivan; Chen, RayBing
 Source:
 Computational statistics & data analysis 2019 v.129 pp. 119134
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; experimental design; models; regression analysis; telescopes; Show all 6 Subjects
 Abstract:
 ... We study a logistic modelbased active learning procedure for binary classification problems, in which we adopt a batch subject selection strategy with a modified sequential experimental design method. Moreover, accompanying the proposed subject selection scheme, we simultaneously conduct a greedy variable selection procedure such that we can update the classification model with all labeled traini ...
 DOI:
 10.1016/j.csda.2018.08.013

http://dx.doi.org/10.1016/j.csda.2018.08.013
 Author:
 Krivitsky, Pavel N.
 Source:
 Computational statistics & data analysis 2017 v.107 pp. 149161
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; Show all 3 Subjects
 Abstract:
 ... Exponentialfamily models for dependent data have applications in a wide variety of areas, but the dependence often results in an intractable likelihood, requiring either analytic approximation or MCMCbased techniques to fit, the latter requiring an initial parameter configuration to seed their simulations. A poor initial configuration can lead to slow convergence or outright failure. The approxi ...
 DOI:
 10.1016/j.csda.2016.10.015

http://dx.doi.org/10.1016/j.csda.2016.10.015
 Author:
 Wang, Ketong; Porter, Michael D.
 Source:
 Computational statistics & data analysis 2018 v.128 pp. 395411
 ISSN:
 01679473
 Subject:
 algorithms, etc ; Bayesian theory; data collection; models; Show all 4 Subjects
 Abstract:
 ... Bayesian modelbased clustering is a widely applied procedure for discovering groups of related observations in a dataset. These approaches use Bayesian mixture models, estimated with MCMC, which provide posterior samples of the model parameters and clustering partition. While inference on model parameters is well established, inference on the clustering partition is less developed. A new method i ...
 DOI:
 10.1016/j.csda.2018.08.002

https://dx.doi.org/10.1016/j.csda.2018.08.002
 Author:
 Zhao, Weihua; Jiang, Xuejun; Lian, Heng
 Source:
 Computational statistics & data analysis 2018 v.127 pp. 269280
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; regression analysis; Show all 4 Subjects
 Abstract:
 ... A principal varyingcoefficient model for quantile regression based on regression splines estimation is proposed. Convergence rate and local asymptotics for the coefficient functions are then derived. Furthermore, penalization is used to obtain joint variable selection and dimension reduction in quantile varyingcoefficient models. A group coordinate descent algorithm is adopted for a computationa ...
 DOI:
 10.1016/j.csda.2018.05.021

http://dx.doi.org/10.1016/j.csda.2018.05.021
 Author:
 Abpeykar, Shadi; Ghatee, Mehdi; Zare, Hadi
 Source:
 Computational statistics & data analysis 2018
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; decision support systems; hydrofluorocarbons; Show all 4 Subjects
 Abstract:
 ... Classification of the highdimensional data is challenging due to the curse of dimensionality, heavy computational burden and decreasing precision of algorithms. In order to mitigate these effects, feature selection approaches that can determine an efficient subset of features are utilized in the processing. However, most of these techniques attain just one subset of nonredundant features includi ...
 DOI:
 10.1016/j.csda.2018.08.015

http://dx.doi.org/10.1016/j.csda.2018.08.015
 Author:
 Wong, Raymond K.W.; Zhang, Xiaoke
 Source:
 Computational statistics & data analysis 2018
 ISSN:
 01679473
 Subject:
 algorithms, etc ; covariance; data collection; ingredients; traffic; Show all 5 Subjects
 Abstract:
 ... In functional data analysis (FDA), the covariance function is fundamental not only as a critical quantity for understanding elementary aspects of functional data but also as an indispensable ingredient for many advanced FDA methods. A new class of nonparametric covariance function estimators in terms of various spectral regularizations of an operator associated with a reproducing kernel Hilbert sp ...
 DOI:
 10.1016/j.csda.2018.05.013

http://dx.doi.org/10.1016/j.csda.2018.05.013
 Author:
 Bermúdez, Lluís; Karlis, Dimitris; Santolino, Miguel
 Source:
 Computational statistics & data analysis 2017 v.112 pp. 1423
 ISSN:
 01679473
 Subject:
 algorithms, etc ; accidents; data collection; models; Show all 4 Subjects
 Abstract:
 ... A new modelling approach, based on finite mixtures of multiple discrete distributions of different multiplicities, is proposed to fit data with a lot of periodic spikes in certain values. An EM algorithm is provided in order to ensure the models’ easeoffit and then a simulation study is presented to show its efficiency. A numerical application with a real data set involving the length, measured ...
 DOI:
 10.1016/j.csda.2017.02.013

http://dx.doi.org/10.1016/j.csda.2017.02.013
 Author:
 FuentesGarcía, Ruth; Mena, Ramsés H.; Walker, Stephen G.
 Source:
 Computational statistics & data analysis 2019 v.137 pp. 92100
 ISSN:
 01679473
 Subject:
 algorithms, etc ; Bayesian theory; Markov chain; Monte Carlo method; data collection; models; Show all 6 Subjects
 Abstract:
 ... Motivated by the Hopfield’s network, a conditional maximization routine is used in order to compute the posterior mode of a random allocation model. The proposed approach applies to a general framework covering parametric and nonparametric Bayesian mixture models, product partition models, and change point models, among others. The resulting algorithm is simple to code and very fast, thus providin ...
 DOI:
 10.1016/j.csda.2019.02.008

https://dx.doi.org/10.1016/j.csda.2019.02.008
 Author:
 Derumigny, Alexis; Fermanian, JeanDavid
 Source:
 Computational statistics & data analysis 2019 v.135 pp. 7094
 ISSN:
 01679473
 Subject:
 algorithms, etc ; artificial intelligence; data collection; decision support systems; neural networks; statistical analysis; Show all 6 Subjects
 Abstract:
 ... It is shown how the problem of estimating conditional Kendall’s tau can be rewritten as a classification task. Conditional Kendall’s tau is a conditional dependence parameter that is a characteristic of a given pair of random variables. The goal is to predict whether the pair is concordant (value of 1) or discordant (value of −1) conditionally on some covariates. The consistency and the asymptotic ...
 DOI:
 10.1016/j.csda.2019.01.013

https://dx.doi.org/10.1016/j.csda.2019.01.013
 Author:
 Yu, Dalei; Ding, Chang; He, Na; Wang, Ruiwu; Zhou, Xiaohua; Shi, Lei
 Source:
 Computational statistics & data analysis 2019 v.129 pp. 93118
 ISSN:
 01679473
 Subject:
 algorithms, etc ; case studies; confidence interval; data collection; metaanalysis; models; quantitative analysis; statistical analysis; variance; Show all 9 Subjects
 Abstract:
 ... Metaanalysis provides a quantitative method for combining results from independent studies with the same treatment. However, existing estimation methods are sensitive to the presence of outliers in the datasets. In this paper we study the robust estimation for the parameters in metaregression, including the betweenstudy variance and regression parameters. Huber’s rho function and Tukey’s biweig ...
 DOI:
 10.1016/j.csda.2018.08.010

http://dx.doi.org/10.1016/j.csda.2018.08.010
 Author:
 Dou, Xiaoling; Kuriki, Satoshi; Lin, Gwo Dong; Richards, Donald
 Source:
 Computational statistics & data analysis 2016 v.93 pp. 228245
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; statistics; Show all 3 Subjects
 Abstract:
 ... A method that uses order statistics to construct multivariate distributions with fixed marginals and which utilizes a representation of the Bernstein copula in terms of a finite mixture distribution is proposed. Expectation–maximization (EM) algorithms to estimate the Bernstein copula are proposed, and a local convergence property is proved. Moreover, asymptotic properties of the proposed semipara ...
 DOI:
 10.1016/j.csda.2014.01.009

http://dx.doi.org/10.1016/j.csda.2014.01.009
 Author:
 Shen, Junshan; Yuen, Kam Chuen; Liu, Chunling
 Source:
 Computational statistics & data analysis 2016 v.93 pp. 285293
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; Show all 2 Subject
 Abstract:
 ... The purpose is to propose a new EM algorithm for doubly censored data subject to nonparametric moment constraints. Empirical likelihood confidence regions are constructed for one or two samples of doubly censored data. It is shown that the corresponding empirical likelihood ratio converges to a standard chisquare random variable. Simulations are carried out to assess the finitesample performan ...
 DOI:
 10.1016/j.csda.2015.01.010

http://dx.doi.org/10.1016/j.csda.2015.01.010
 Author:
 Martinez, Waldyn; Gray, J. Brian
 Source:
 Computational statistics & data analysis 2016 v.93 pp. 483497
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; Show all 3 Subjects
 Abstract:
 ... Boosting refers to a family of methods that combine sequences of individual classifiers into highly accurate ensemble models through weighted voting. AdaBoost, short for “Adaptive Boosting”, is the most wellknown boosting algorithm. AdaBoost has many strengths. Among them, there is sufficient empirical evidence pointing to its performance being generally superior to that of individual classifiers ...
 DOI:
 10.1016/j.csda.2015.06.010

http://dx.doi.org/10.1016/j.csda.2015.06.010
 Author:
 Marbac, Matthieu; Sedki, Mohammed
 Source:
 Computational statistics & data analysis 2017 v.114 pp. 130145
 ISSN:
 01679473
 Subject:
 algorithms, etc ; computer software; data collection; models; probability; Show all 5 Subjects
 Abstract:
 ... A new family of onefactor distributions for modeling highdimensional binary data is introduced. The model provides an explicit probability for each event, thus avoiding the numeric approximations often made by existing methods. Model interpretation is easy, because each variable is described by two continuous parameters (corresponding to the marginal probability and to the strength of dependency ...
 DOI:
 10.1016/j.csda.2017.04.010

http://dx.doi.org/10.1016/j.csda.2017.04.010
 Author:
 Doove, Lisa L.; Wilderjans, Tom F.; Calcagnì, Antonio; Van Mechelen, Iven
 Source:
 Computational statistics & data analysis 2017 v.107 pp. 8191
 ISSN:
 01679473
 Subject:
 algorithms, etc ; biostatistics; data collection; models; statistical analysis; Show all 5 Subjects
 Abstract:
 ... In benchmarking studies with simulated data sets in which two or more statistical methods are compared, over and above the search of a universally winning method, one may investigate how the winning method may vary over patterns of characteristics of the data or the datagenerating mechanism. Interestingly, this problem bears strong formal similarities to the problem of looking for optimal treatme ...
 DOI:
 10.1016/j.csda.2016.10.016

http://dx.doi.org/10.1016/j.csda.2016.10.016
 Author:
 Chauveau, Didier; Hoang, Vy Thuy Lynh
 Source:
 Computational statistics & data analysis 2016 v.103 pp. 116
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; mathematical models; Show all 3 Subjects
 Abstract:
 ... Models and algorithms for nonparametric estimation of finite multivariate mixtures have been recently proposed, where it is usually assumed that coordinates are independent conditional on the subpopulation from which each observation is drawn. Hence in these models the dependence structure comes only from the mixture. This assumption is relaxed, allowing for independent multivariate blocks of coor ...
 DOI:
 10.1016/j.csda.2016.04.013

http://dx.doi.org/10.1016/j.csda.2016.04.013
 Author:
 GarcíaEscudero, Luis Angel; Gordaliza, Alfonso; Greselin, Francesca; Ingrassia, Salvatore; MayoIscar, Agustín
 Source:
 Computational statistics & data analysis 2016 v.99 pp. 131147
 ISSN:
 01679473
 Subject:
 algorithms, etc ; covariance; data collection; models; Show all 4 Subjects
 Abstract:
 ... Mixtures of Gaussian factors are powerful tools for modeling an unobserved heterogeneous population, offering–at the same time–dimension reduction and modelbased clustering. The high prevalence of spurious solutions and the disturbing effects of outlying observations in maximum likelihood estimation may cause biased or misleading inferences. Restrictions for the component covariances are consider ...
 DOI:
 10.1016/j.csda.2016.01.005

http://dx.doi.org/10.1016/j.csda.2016.01.005
 Author:
 Tang, Qingguo; Karunamuni, Rohana J.
 Source:
 Computational statistics & data analysis 2016 v.94 pp. 4962
 ISSN:
 01679473
 Subject:
 algorithms, etc ; computational methodology; data collection; Show all 3 Subjects
 Abstract:
 ... Standard kernel density and regression estimators are wellknown to be computationally very slow when analyzing large data sets, and algorithms that achieve considerable computational savings are highly desirable. With this goal in mind, two fast and accurate computational methods are proposed in this paper for computation of univariate and multivariate local polynomial estimators defined on an eq ...
 DOI:
 10.1016/j.csda.2015.07.015

http://dx.doi.org/10.1016/j.csda.2015.07.015
 Author:
 Vinué, Guillermo; Epifanio, Irene; Alemany, Sandra
 Source:
 Computational statistics & data analysis 2015 v.87 pp. 102115
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; Show all 2 Subject
 Abstract:
 ... The new concept archetypoids is introduced. Archetypoid analysis represents each observation in a dataset as a mixture of actual observations in the dataset, which are pure type or archetypoids. Unlike archetype analysis, archetypoids are real observations, not a mixture of observations. This is relevant when existing archetypal observations are needed, rather than fictitious ones. An algorithm is ...
 DOI:
 10.1016/j.csda.2015.01.018

http://dx.doi.org/10.1016/j.csda.2015.01.018
 Author:
 Wang, WanLun
 Source:
 Computational statistics & data analysis 2015 v.83 pp. 223235
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; Show all 3 Subjects
 Abstract:
 ... Mixtures of common tfactor analyzers (MCtFA) have emerged as a sound parsimonious modelbased tool for robust modeling of highdimensional data in the presence of fattailed noises and atypical observations. This paper presents a generalization of MCtFA to accommodate missing values as they frequently occur in many scientific researches. Under a missing at random mechanism, a computationally effi ...
 DOI:
 10.1016/j.csda.2014.10.007

http://dx.doi.org/10.1016/j.csda.2014.10.007
 Author:
 Li, Peili; Xiao, Yunhai
 Source:
 Computational statistics & data analysis 2018 v.128 pp. 292307
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; multivariate analysis; system optimization; variance covariance matrix; Show all 6 Subjects
 Abstract:
 ... Estimating large and sparse inverse covariance matrix plays a fundamental role in modern multivariate analysis, because the zero entries capture the conditional independence between pairs of variables given all other variables. This estimation task can be realized by penalizing the maximum likelihood estimation with an adaptive group lasso penalty imposed directly on the elements of the inverse, w ...
 DOI:
 10.1016/j.csda.2018.07.011

https://dx.doi.org/10.1016/j.csda.2018.07.011
 Author:
 Chen, ChyongMei; Shen, Paosheng; Tseng, YiKuan
 Source:
 Computational statistics & data analysis 2018 v.128 pp. 116127
 ISSN:
 01679473
 Subject:
 algorithms, etc ; Human immunodeficiency virus; biomarkers; clinical trials; cohort studies; data collection; models; statistical analysis; Show all 8 Subjects
 Abstract:
 ... In many clinical trials and epidemiology research, subjects are followedup repeatedly, and repeated measurements on longitudinal covariates as well as an observation on a possibly censored timetoevent are collected on each subject. The longitudinal covariates are often measured intermittently with measurement errors, and the measurement process is terminated by a correlated event process, leadi ...
 DOI:
 10.1016/j.csda.2018.07.001

https://dx.doi.org/10.1016/j.csda.2018.07.001
 Author:
 Wang, Shangshan; Xiang, Liming
 Source:
 Computational statistics & data analysis 2017 v.115 pp. 136154
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; gene expression; models; regression analysis; system optimization; Show all 6 Subjects
 Abstract:
 ... We advocate linear regression by modeling the error term through a finite mixture of asymmetric Laplace distributions (ALDs). The model expands the flexibility of linear regression to account for heterogeneity among data and allows us to establish the equivalence between maximum likelihood estimation of the model parameters and the composite quantile regression (CQR) estimation developed by Zou an ...
 DOI:
 10.1016/j.csda.2017.06.002

http://dx.doi.org/10.1016/j.csda.2017.06.002
 Author:
 Kojadinovic, Ivan
 Source:
 Computational statistics & data analysis 2017 v.112 pp. 2441
 ISSN:
 01679473
 Subject:
 algorithms, etc ; Monte Carlo method; data collection; insurance; models; Show all 5 Subjects
 Abstract:
 ... When modeling the distribution of a multivariate continuous random vector using the socalled copula approach, it is not uncommon to have ties in the coordinate samples of the available data because of rounding or lack of measurement precision. Yet, the vast majority of existing inference procedures on the underlying copula were both theoretically derived and practically implemented under the assu ...
 DOI:
 10.1016/j.csda.2017.02.006

http://dx.doi.org/10.1016/j.csda.2017.02.006
 Author:
 Ippel, L.; Kaptein, M.C.; Vermunt, J.K.
 Source:
 Computational statistics & data analysis 2016 v.104 pp. 169182
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; mobile telephones; models; schools; Show all 5 Subjects
 Abstract:
 ... Multilevel models are often used for the analysis of grouped data. Grouped data occur for instance when estimating the performance of pupils nested within schools or analyzing multiple observations nested within individuals. Currently, multilevel models are mostly fit to static datasets. However, recent technological advances in the measurement of social phenomena have led to data arriving in a co ...
 DOI:
 10.1016/j.csda.2016.06.008

http://dx.doi.org/10.1016/j.csda.2016.06.008
 Author:
 Gruenhage, Gina; Opper, Manfred; Barthelme, Simon
 Source:
 Computational statistics & data analysis 2016 v.104 pp. 5165
 ISSN:
 01679473
 Subject:
 algorithms, etc ; artificial intelligence; data collection; topology; Show all 4 Subjects
 Abstract:
 ... Most Machine Learning (ML) methods, from clustering to classification, rely on a distance function to describe relationships between datapoints. For complex datasets it is hard to avoid making some arbitrary choices when defining a distance function. To compare images, one must choose a spatial scale, for signals, a temporal scale. The right scale is hard to pin down and it is preferable when resu ...
 DOI:
 10.1016/j.csda.2016.06.006

http://dx.doi.org/10.1016/j.csda.2016.06.006
 Author:
 Mount, David M.; Netanyahu, Nathan S.; Piatko, Christine D.; Wu, Angela Y.; Silverman, Ruth
 Source:
 Computational statistics & data analysis 2016 v.99 pp. 148170
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; linear models; probability analysis; Show all 4 Subjects
 Abstract:
 ... The linear least trimmed squares (LTS) estimator is a statistical technique for fitting a linear model to a set of points. It was proposed by Rousseeuw as a robust alternative to the classical least squares estimator. Given a set of n points in Rd, the objective is to minimize the sum of the smallest 50% squared residuals (or more generally any given fraction). There exist practical heuristics for ...
 DOI:
 10.1016/j.csda.2016.01.016

http://dx.doi.org/10.1016/j.csda.2016.01.016
 Author:
 Bongiorno, Enea G.; Goia, Aldo
 Source:
 Computational statistics & data analysis 2016 v.99 pp. 204222
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; probability; probability distribution; Show all 4 Subjects
 Abstract:
 ... An unsupervised and a supervised classification approach for Hilbert random curves are studied. Both rest on the use of a surrogate of the probability density which is defined, in a distributionfree mixture context, from an asymptotic factorization of the smallball probability. That surrogate density is estimated by a kernel approach from the principal components of the data. The focus is on the ...
 DOI:
 10.1016/j.csda.2016.01.019

http://dx.doi.org/10.1016/j.csda.2016.01.019
 Author:
 Leung, Andy; Zhang, Hongyang; Zamar, Ruben
 Source:
 Computational statistics & data analysis 2016 v.99 pp. 111
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; regression analysis; Show all 4 Subjects
 Abstract:
 ... Cellwise outliers are likely to occur together with casewise outliers in modern datasets of relatively large dimension. Recent work has shown that traditional robust regression methods may fail when applied to such datasets. We propose a new robust regression procedure to deal with casewise and cellwise outliers. The proposed method, called threestep regression, proceeds as follows: first, it use ...
 DOI:
 10.1016/j.csda.2016.01.004

http://dx.doi.org/10.1016/j.csda.2016.01.004
 Author:
 Secchi, Piercesare; Vantini, Simone; Zanini, Paolo
 Source:
 Computational statistics & data analysis 2016 v.95 pp. 133149
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; electroencephalography; independent component analysis; Show all 4 Subjects
 Abstract:
 ... A new method named Hierarchical Independent Component Analysis is presented, particularly suited for dealing with two problems regarding the analysis of highdimensional and complex data: dimensional reduction and multiresolution analysis. It takes into account the Blind Source Separation framework, where the purpose is the research of a basis for a dimensional reduced space to represent data, wh ...
 DOI:
 10.1016/j.csda.2015.09.014

http://dx.doi.org/10.1016/j.csda.2015.09.014
 Author:
 Nguyen, Hien D.; McLachlan, Geoffrey J.
 Source:
 Computational statistics & data analysis 2016 v.93 pp. 177191
 ISSN:
 01679473
 Subject:
 algorithms, etc ; climate; data collection; models; normal distribution; Show all 5 Subjects
 Abstract:
 ... Mixture of Linear Experts (MoLE) models provide a popular framework for modeling nonlinear regression data. The majority of applications of MoLE models utilizes a Gaussian distribution for regression error. Such assumptions are known to be sensitive to outliers. The use of a Laplace distributed error is investigated. This model is named the Laplace MoLE (LMoLE). Links are drawn between the Laplace ...
 DOI:
 10.1016/j.csda.2014.10.016

http://dx.doi.org/10.1016/j.csda.2014.10.016
 Author:
 Fernández, D.; Arnold, R.; Pledger, S.
 Source:
 Computational statistics & data analysis 2016 v.93 pp. 4675
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; multivariate analysis; Show all 4 Subjects
 Abstract:
 ... Many of the methods which deal with the reduction of dimensionality in matrices of data are based on mathematical techniques such as distancebased algorithms or matrix decomposition and eigenvalues. Recently a group of likelihoodbased finite mixture models for a data matrix with binary or count data, using basic Bernoulli or Poisson building blocks has been developed. This is extended and establ ...
 DOI:
 10.1016/j.csda.2014.11.004

http://dx.doi.org/10.1016/j.csda.2014.11.004
 Author:
 Melnykov, Volodymyr
 Source:
 Computational statistics & data analysis 2016 v.93 pp. 3145
 ISSN:
 01679473
 Subject:
 algorithms, etc ; Markov chain; data collection; dynamic models; Show all 4 Subjects
 Abstract:
 ... Navigation patterns expressed by sequences of visited websites or categories can characterize the behavior and habits of users. Such webpage routes taken by individuals are commonly called clickstreams. Clustering clickstream sequences is a recent yet challenging problem with many applications. The main difficulty is related to the fact that one needs to group categorical data sequences rather t ...
 DOI:
 10.1016/j.csda.2014.09.016

http://dx.doi.org/10.1016/j.csda.2014.09.016
 Author:
 Černý, Michal; Hladík, Milan
 Source:
 Computational statistics & data analysis 2014 v.80 pp. 2643
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; variance; Show all 3 Subjects
 Abstract:
 ... The main question is how to compute the upper and lower limits of the range of possible values of a given statistic, when the data range over given intervals. Initially some wellknown statistics, such as sample mean, sample variance or Fratio, are considered in order to illustrate that in some cases the limits can be computed efficiently, while in some cases their computation is NPhard. Subsequ ...
 DOI:
 10.1016/j.csda.2014.06.007

http://dx.doi.org/10.1016/j.csda.2014.06.007
 Author:
 Marés, Jordi; Shlomo, Natalie
 Source:
 Computational statistics & data analysis 2014 v.79 pp. 113
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; risk; Show all 3 Subjects
 Abstract:
 ... Dissemination of data with sensitive information has an implicit risk of unauthorized disclosure. Several masking methods have been developed in order to protect the data without the loss of too much information. One such method is the Post Randomization Method (PRAM) based on perturbations of a categorical variable according to a Markov probability transition matrix. The method has the drawback t ...
 DOI:
 10.1016/j.csda.2014.05.002

http://dx.doi.org/10.1016/j.csda.2014.05.002
 Author:
 Eugster, Manuel J.A.; Leisch, Friedrich; Strobl, Carolin
 Source:
 Computational statistics & data analysis 2014 v.71 pp. 9861000
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; Show all 3 Subjects
 Abstract:
 ... It is common knowledge that the performance of different learning algorithms depends on certain characteristics of the data—such as dimensionality, linear separability or sample size. However, formally investigating this relationship in an objective and reproducible way is not trivial. A new formal framework for describing the relationship between data set characteristics and the performance of di ...
 DOI:
 10.1016/j.csda.2013.08.007

http://dx.doi.org/10.1016/j.csda.2013.08.007
 Author:
 Asquith, William H.
 Source:
 Computational statistics & data analysis 2014 v.71 pp. 955970
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; statistical analysis; Show all 3 Subjects
 Abstract:
 ... The implementation characteristics of two method of Lmoments (MLM) algorithms for parameter estimation of the 4parameter Asymmetric Exponential Power (AEP4) distribution are studied using the R environment for statistical computing. The objective is to validate the algorithms for general application of the AEP4 using R. An algorithm was introduced in the original study of the Lmoments for the A ...
 DOI:
 10.1016/j.csda.2012.12.013

http://dx.doi.org/10.1016/j.csda.2012.12.013
 Author:
 Song, Weixing; Yao, Weixin; Xing, Yanru
 Source:
 Computational statistics & data analysis 2014 v.71 pp. 128137
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; regression analysis; Show all 3 Subjects
 Abstract:
 ... A robust estimation procedure for mixture linear regression models is proposed by assuming that the error terms follow a Laplace distribution. Using the fact that the Laplace distribution can be written as a scale mixture of a normal and a latent distribution, this procedure is implemented by an EM algorithm which incorporates two types of missing information from the mixture class membership and ...
 DOI:
 10.1016/j.csda.2013.06.022

http://dx.doi.org/10.1016/j.csda.2013.06.022
 Author:
 Prater, Ashley; Shen, Lixin; Suter, Bruce W.
 Source:
 Computational statistics & data analysis 2015 v.90 pp. 3646
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; mathematical models; regression analysis; Show all 4 Subjects
 Abstract:
 ... A simple iterative method for finding the Dantzig selector, designed for linear regression problems, is introduced. The method consists of two stages. The first stage approximates the Dantzig selector through a fixedpoint formulation of solutions to the Dantzig selector problem; the second stage constructs a new estimator by regressing data onto the support of the approximated Dantzig selector. T ...
 DOI:
 10.1016/j.csda.2015.04.005

http://dx.doi.org/10.1016/j.csda.2015.04.005
 Author:
 Yue, Chen; Chen, Shaojie; Sair, Haris I.; Airan, Raag; Caffo, Brian S.
 Source:
 Computational statistics & data analysis 2015 v.89 pp. 126133
 ISSN:
 01679473
 Subject:
 algorithms, etc ; Markov chain; data collection; models; Show all 4 Subjects
 Abstract:
 ... Data reproducibility is a critical issue in all scientific experiments. In this manuscript, the problem of quantifying the reproducibility of graphical measurements is considered. The image intraclass correlation coefficient (I2C2) is generalized and the graphical intraclass correlation coefficient (GICC) is proposed for such purpose. The concept for GICC is based on multivariate probitlinear m ...
 DOI:
 10.1016/j.csda.2015.02.012

http://dx.doi.org/10.1016/j.csda.2015.02.012
 Author:
 Bürgin, Reto; Ritschard, Gilbert
 Source:
 Computational statistics & data analysis 2015 v.86 pp. 6580
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; regression analysis; unemployment; Show all 4 Subjects
 Abstract:
 ... A treebased algorithm for longitudinal regression analysis that aims to learn whether and how the effects of predictor variables depend on moderating variables is presented. The algorithm is based on multivariate generalized linear mixed models and it builds piecewise constant coefficient functions. Moreover, it is scalable for many moderators of possibly mixed scales, integrates interactions bet ...
 DOI:
 10.1016/j.csda.2015.01.003

http://dx.doi.org/10.1016/j.csda.2015.01.003
 Author:
 Ding, Jieli; Tian, GuoLiang; Yuen, Kam Chuen
 Source:
 Computational statistics & data analysis 2015 v.84 pp. 135151
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; models; regression analysis; Show all 4 Subjects
 Abstract:
 ... The constrained estimation in Cox’s model for the rightcensored survival data is studied and the asymptotic properties of the constrained estimators are derived by using the Lagrangian method based on Karush–Kuhn–Tucker conditions. A novel minorization–maximization (MM) algorithm is developed for calculating the maximum likelihood estimates of the regression coefficients subject to box or linear ...
 DOI:
 10.1016/j.csda.2014.11.005

http://dx.doi.org/10.1016/j.csda.2014.11.005
 Author:
 Feng, Sanying; Lian, Heng; Xue, Liugen
 Source:
 Computational statistics & data analysis 2016 v.102 pp. 98109
 ISSN:
 01679473
 Subject:
 algorithms, etc ; data collection; linear models; variance covariance matrix; Show all 4 Subjects
 Abstract:
 ... In this paper, we propose a nested modified Cholesky decomposition for modeling the covariance structure in multivariate longitudinal data analysis. The entries of this decomposition have simple structures and can be interpreted as the generalized moving average coefficient matrices and innovation covariance matrices. We model the elements of these matrices by a class of unconstrained linear model ...
 DOI:
 10.1016/j.csda.2016.04.006

http://dx.doi.org/10.1016/j.csda.2016.04.006