Displaying similar documents to “Covariance Structure of Principal Components for Three-Part Compositional Data”

Analytical representation of ellipses in the Aitchison geometry and its application

Karel Hron (2009)

Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica

Similarity:

Compositional data, multivariate observations that hold only relative information, need a special treatment while performing statistical analysis, with respect to the simplex as their sample space ([Aitchison, J.: The Statistical Analysis of Compositional Data. Chapman and Hall, London, 1986.], [Aitchison, J., Greenacre, M.: Biplots of compositional data. Applied Statistics 51 (2002), 375–392.], [Buccianti, A., Mateu-Figueras, G., Pawlowsky-Glahn, V. (eds): Compositional data analysis...

Ridge estimation of covariance matrix from data in two classes

Yi Zhou, Bin Zhang (2024)

Applications of Mathematics

Similarity:

This paper deals with the problem of estimating a covariance matrix from the data in two classes: (1) good data with the covariance matrix of interest and (2) contamination coming from a Gaussian distribution with a different covariance matrix. The ridge penalty is introduced to address the problem of high-dimensional challenges in estimating the covariance matrix from the two-class data model. A ridge estimator of the covariance matrix has a uniform expression and keeps positive-definite,...

Protecting micro-data by micro-aggregation: the experience in Eurostat.

Daniel Defays (1997)

Qüestiió

Similarity:

A natural strategy to protect the confidentiality of individual data is to aggregate them at the lowest possible level. Some studies realised in Eurostat on this topic will be presented: properties of classifications in clusters of fixed sizes, micro-aggregation as a generic method to protect the confidentiality of individual data, application to the Community Innovation Survey. The work performed in Eurostat will be put in line with other projects conducted at European level on the...

Distance-based regression in prediction of solar flare activity.

Anna Bartkowiak, Maria Jakimiec (1994)

Qüestiió

Similarity:

Short-term prediction of solar flare activity using multiple regression methods was considered. The variables describing active regions the given day were used to predict the flare activity on the next day. Two groups of observational data covering the years 1988 and 1989 were dealt with. Some variants of the distance-based regression as proposed by Cuadras and Arenas (1990) appeared to be superior to the ordinary least squares method by describing more accurately the data sets under...

Profile analysis of mothers susceptible to contaminant exposure in the Algarve region: Application of the HJ-BIPLOT method

A. Serafim, R. Company, B. Lopes, N. Silva, E. Castela, M.J. Bebianno, G. Castela (2012)

Biometrical Letters

Similarity:

The HJ-BIPLOT method developed by Galindo (1986) was applied in order to identify and categorize mothers vulnerable to environmental contamination in the Algarve region (South Portugal). The application of the BIPLOT method made it possible to recognize the most important exposure routes for contamination, showing that workplace, diet and smoking habits seem the most significant factors contributing to maternal and foetal exposure vulnerability

Regularization for high-dimensional covariance matrix

Xiangzhao Cui, Chun Li, Jine Zhao, Li Zeng, Defei Zhang, Jianxin Pan (2016)

Special Matrices

Similarity:

In many applications, high-dimensional problem may occur often for various reasons, for example, when the number of variables under consideration is much bigger than the sample size, i.e., p >> n. For highdimensional data, the underlying structures of certain covariance matrix estimates are usually blurred due to substantial random noises, which is an obstacle to draw statistical inferences. In this paper, we propose a method to identify the underlying covariance structure by regularizing...

Expert knowledge and data analysis for detecting advanced persistent threats

Juan Ramón Moya, Noemí DeCastro-García, Ramón-Ángel Fernández-Díaz, Jorge Lorenzana Tamargo (2017)

Open Mathematics

Similarity:

Critical Infrastructures in public administration would be compromised by Advanced Persistent Threats (APT) which today constitute one of the most sophisticated ways of stealing information. This paper presents an effective, learning based tool that uses inductive techniques to analyze the information provided by firewall log files in an IT infrastructure, and detect suspicious activity in order to mark it as a potential APT. The experiments have been accomplished mixing real and synthetic...

Bayesian joint modelling of the mean and covariance structures for normal longitudinal data.

Edilberto Cepeda-Cuervo, Vicente Nunez-Anton (2007)

SORT

Similarity:

We consider the joint modelling of the mean and covariance structures for the general antedependence model, estimating their parameters and the innovation variances in a longitudinal data context. We propose a new and computationally efficient classic estimation method based on the Fisher scoring algorithm to obtain the maximum likelihood estimates of the parameters. In addition, we also propose a new and innovative Bayesian methodology based on the Gibbs sampling, properly adapted for...

Correspondence analysis and two-way clustering.

Antonio Ciampi, Ana González Marcos, Manuel Castejón Limas (2005)

SORT

Similarity:

Correspondence analysis followed by clustering of both rows and columns of a data matrix is proposed as an approach to two-way clustering. The novelty of this contribution consists of: i) proposing a simple method for the selecting of the number of axes; ii) visualizing the data matrix as is done in micro-array analysis; iii) enhancing this representation by emphasizing those variables and those individuals which are 'well represented' in the subspace of the chosen axes. The approach...