Cross-sectional averages versus principal components

In spite of the increased use of factor-augmented regressions in recent years, little is known regarding the relative merits of the two main approaches to estimation and inference, namely, the cross-sectional average and principal component estimators. By providing a formal comparison of the approaches, the current paper fills this gap in the literature.

A comparison of the dietary patterns derived by principal component analysis and cluster analysis in older Australians

BACKGROUND: Despite increased use of dietary pattern methods in nutritional epidemiology, there have been few direct comparisons of methods. Older adults are a particularly understudied population in the dietary pattern literature. This study aimed to compare dietary patterns derived by principal component analysis (PCA) and cluster analysis (CA) in older adults and to examine their associations with socio-demographic and health behaviours. METHODS: Men (n = 1888) and women (n = 2071) aged 55-65 years completed a 111-item food frequency questionnaire in 2010. Food items were collapsed into 52 food groups and dietary patterns were determined by PCA and CA. Associations between dietary patterns and participant characteristics were examined using Chi-square analysis. The standardised PCA-derived dietary patterns were compared across the clusters using one-way ANOVA. RESULTS: PCA identified four dietary patterns in men and two dietary patterns in women. CA identified three dietary patterns in both men and women. Men in cluster 1 (fruit, vegetables, wholegrains, fish and poultry) scored higher on PCA factor 1 (vegetable dishes, fruit, fish and poultry) and factor 4 (vegetables) compared to factor 2 (spreads, biscuits, cakes and confectionery) and factor 3 (red meat, processed meat, white-bread and hot chips) (mean, 95 % CI; 0.92, 0.82-1.02 vs. 0.74, 0.63-0.84 vs. -0.43, -0.50- -0.35 vs. 0.60 0.46-0.74, respectively). Women in cluster 1 (fruit, vegetables and fish) scored highest on PCA factor 1 (fruit, vegetables and fish) compared to factor 2 (processed meat, hot chips cakes and confectionery) (1.05, 0.97-1.14 vs. -0.14, -0.21- -0.07, respectively). Cluster 3 (small eaters) in both men and women had negative factor scores for all the identified PCA dietary patterns. Those with dietary patterns characterised by higher consumption of red and processed meat and refined grains were more likely to be Australian-born, have a lower level of education, a higher BMI, smoke and did not meet physical activity recommendations (all P < 0.05). CONCLUSIONS: PCA and CA identified comparable dietary patterns within older Australians. However, PCA may provide some advantages compared to CA with respect to interpretability of the resulting dietary patterns. Older adults with poor dietary patterns also displayed other negative lifestyle behaviours. Food-based dietary pattern methods may inform dietary advice that is understood by the community.

Neuronal Assembly Detection and Cell Membership Specification by Principal Component Analysis

LOPES-DOS-SANTOS, V. , CONDE-OCAZIONEZ, S. ; NICOLELIS, M. A. L. , RIBEIRO, S. T. , TORT, A. B. L. . Neuronal assembly detection and cell membership specification by principal component analysis. Plos One, v. 6, p. e20996, 2011.

Reduction capability of soil humic substances from the Rio Negro basin, Brazil, towards Hg(II) studied by a multimethod approach and principal component analysis (PCA)

This paper characterizes humic substances (HS) extracted from soil samples collected in the Rio Negro basin in the state of Amazonas, Brazil, particularly investigating their reduction capabilities towards Hg(II) in order to elucidate potential mercury cycling/volatilization in this environment. For this reason, a multimethod approach was used, consisting of both instrumental methods (elemental analysis, EPR, solid-state NMR, FIA combined with cold-vapor AAS of Hg(0)) and statistical methods such as principal component analysis (PCA) and a central composite factorial planning method. The HS under study were divided into groups, complexing and reducing ones, owing to different distribution of their functionalities. The main functionalities (cor)related with reduction of Hg(II) were phenolic, carboxylic and amide groups, while the groups related with complexation of Hg(II) were ethers, hydroxyls, aldehydes and ketones. The HS extracted from floodable regions of the Rio Negro basin presented a greater capacity to retain (to complex, to adsorb physically and/or chemically) Hg(II), while nonfloodable regions showed a greater capacity to reduce Hg(II), indicating that HS extracted from different types of regions contribute in different ways to the biogeochemical mercury cycle in the basin of the mid-Rio Negro, AM, Brazil. (c) 2007 Published by Elsevier B.V.

Utilização de métodos estatísticos multivariados na caracterização do mosaico sucessional em floresta semidecídual

O presente trabalho objetivou verificar a possibilidade da utilização de métodos estatísticos multivariados na caracterização das fases do desenvolvimento do mosaico sucessional de um trecho de floresta estacional semidecidual, através de variáveis estruturais. Foram alocadas parcelas de 10 m x 10 m, em que se procedeu à análise estrutural, ou seja, levantamento fitossociológico acrescido das variáveis Porcentagem de Cobertura (PC), Altura do Dossel (AD) e Cobertura por Lianas (CL). Os métodos estatísticos empregados foram Análise de Componentes Principais e Análise de Agrupamento, mais especificamente Classificação Hierárquica Ascendente. O primeiro componente principal explicou 43,96% da variância total, enquanto o segundo, 25,66%. As variáveis Área Basal (AB), Diâmetro Médio (DM) e Dominância Média (DOM) apresentaram correlações positivas entre si superiores a 0,75, podendo ser DM e DOM consideradas como um grupo de variáveis. As variáveis Número de Indivíduos (NI) e Número de Espécies (NE) apresentaram correlação 0,60, enquanto AD, CL e PC baixas correlações com as demais, indicando a importância da inclusão destas na análise. A classificação hierárquica e a partição dos grupos em quatro foram feitas considerando os dois primeiros eixos fatoriais. Os resultados indicaram dois comportamentos diferenciados: 1) valores baixos para AD e AB: Grupo 1, com valores baixos também para NI, NE e PC (fase de clareira); e Grupo 2, com valores elevados para NI e CL e baixos para DOM e DM (fase de construção); e 2) valores altos para AD e AB: Grupo 3, com valores altos também para NI, NE e PC e valor baixo para CL (fase madura); e Grupo 4, com valores elevados para DOM e DM e mais baixos para CL (fase de degradação). Os métodos estatísticos multivariados permitiram caracterizar as fases do desenvolvimento do mosaico sucessional, através das variáveis estruturais. A forma como foram estimadas as variáveis AD, CL e PC, porém, deve ser aprimorada, assim como é preciso incluir variáveis que discriminem melhor cada fase.

Mapping quantitative trait loci in Gallus gallus using principal components

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

An improved tabu-based vector optimal algorithm for design optimizations of electromagnetic devices

This paper introduces an improved tabu-based vector optimal algorithm for multiobjective optimal designs of electromagnetic devices. The improvements include a division of the entire search process, a new method for fitness assignment, a novel scheme for the generation and selection of neighborhood solutions, and so forth. Numerical results on a mathematical function and an engineering multiobjective design problem demonstrate that the proposed method can produce virtually the exact Pareto front, in both parameter and objective spaces, even though the iteration number used by it is only about 70% of that required by its ancestor.

Chemosystematic studies of natural compounds isolated from Asteraceae: characterization of tribes by principal component analysis

This work describes an application of principal component analysis (PCA) on a database of secondary metabolites from the Asteraceae family. The numbers of occurrences of metabolites in 11 chemical classes for the different vibes of the family were used as variables, PCA allows the identification of chemical classes that contribute most to the subgroups classification within the family. Relationships between chemical composition and botanical classification were made. (C) 2001 Elsevier B.V. B.V. All rights reserved.

Statistical methods applied to the analysis of blasting vibrations in a diabase quarry in the city of Campinas, (SP) Brazil

Statistical methods of multiple regression analysis, trend surface analysis and principal components analysis were applied to seismographic data recorded during production blasting at a diabase quarry in the urban area of Campinas (SP), Brazil. The purpose of these analyses was to determine the influence of the following variables: distance (D), charge weight per delay (W), and scaled distance (SD) associated with properties of the rock body (orientation, frequency and angle of geological discontinuities; depth of bedrock and thickness of the soil overburden) in the variation of the peak particle velocity (PPV). This approach yielded variables with larger influences (loads) on the variation of ground vibration, as well as behavior and space tendency of this variation. The results showed a better relationship between PPV and D, with D being the most important factor in the attenuation of the ground vibrations. The geological joints and the depth to bedrock have a larger influence than the explosive charges in the variation of the vibration levels, but frequencies appear to be more influenced by the amount of soil overburden.

The use of principal components and univariate charts to control multivariate processes

In this article, we evaluate the performance of the T2 chart based on the principal components (PC chart) and the simultaneous univariate control charts based on the original variables (SU X̄ charts) or based on the principal components (SUPC charts). The main reason to consider the PC chart lies on the dimensionality reduction. However, depending on the disturbance and on the way the original variables are related, the chart is very slow in signaling, except when all variables are negatively correlated and the principal component is wisely selected. Comparing the SU X̄, the SUPC and the T 2 charts we conclude that the SU X̄ charts (SUPC charts) have a better overall performance when the variables are positively (negatively) correlated. We also develop the expression to obtain the power of two S 2 charts designed for monitoring the covariance matrix. These joint S2 charts are, in the majority of the cases, more efficient than the generalized variance |S| chart.

Genetic parameters and principal component analysis for egg production from White Leghorn hens

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Diversidade fenotípica e molecular de cultivares brasileiras de soja portadoras de gene RR

Pós-graduação em Agronomia (Genética e Melhoramento de Plantas) - FCAV

Desenvolvimento de métodos de processamento e inteligência computacional no ECG ambulatorial

A monitorização ambulatorial do eletrocardiograma (ECG) permite seguir as atividades cotidianas do paciente durante períodos de 24 horas (ou ainda maiores) possibilitando o estudo de casos que pudessem ter episódios arrítmicos fatais. Entretanto, o maior desafio tecnológico que este tipo de monitorização enfrenta é a perda de informação pela presença de ruídos e artefatos quando o paciente se move. A análise do intervalo QT de despolarização e repolarização ventricular do eletrocardiograma superficial é uma técnica não invasiva com um grande valor para a diagnose e prognósticos de cardiopatias e neuropatias, assim como para a predição da morte cardíaca súbita. A análise do desvio padrão do intervalo QT proporciona informação sobre a dispersão (temporal ou espacial) da repolarização ventricular, entretanto a influencia do ruído provoca erros na detecção do final da onda T que são apreciáveis devido ao fato dos valores pequenos do desvio padrão do QT tanto para sujeitos patológicos e quanto para os sãos. O objetivo geral desta tese é melhorar os métodos de processamento do sinal de ECG ambulatorial usando inteligência computacional, especificamente os métodos relacionados com a detecção do final da onda T, e os de reconhecimento morfológico de batimentos que invalidam a análise da variabilidade do intervalo QT. É proposto e validado (em termos de exatidão e precisão) um novo método e algoritmo para estimar o final da onda T baseado no calculo de áreas de trapézios, empregando sinais da base de dados QT da Physionet. O desempenho do método proposto foi testado e comparado com um dos métodos mais usados para detectar o final da onda T: o método baseado no limiar na primeira derivada. O método de inteligência computacional sugerido combina a extração de características usando o método de análise de componentes principais não lineares e a rede neural de tipo perceptron multicamada. O método de áreas de trapézios teve um bom desempenho em condições ruidosas e não depende de nenhum limiar empírico, sendo adequado para situações com níveis de elevados de ruído de banda larga. O método de reconhecimento morfológico de batimentos foi avaliado com sinais ambulatoriais com e sem artefatos pertencentes a bases de dados de prestigio internacional, e mostrou um bom desempenho.

Classificador Fisherface Fuzzy para o reconhecimento de faces

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Why is it so difficult to identify a single indicator of water stress in plants? A proposal for a multivariate analysis to assess emergent properties

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)