A mixture model-based approach to the clustering of microarray expression data

Motivation: This paper introduces the software EMMIX-GENE that has been developed for the specific purpose of a model-based approach to the clustering of microarray expression data, in particular, of tissue samples on a very large number of genes. The latter is a nonstandard problem in parametric cluster analysis because the dimension of the feature space (the number of genes) is typically much greater than the number of tissues. A feasible approach is provided by first selecting a subset of the genes relevant for the clustering of the tissue samples by fitting mixtures of t distributions to rank the genes in order of increasing size of the likelihood ratio statistic for the test of one versus two components in the mixture model. The imposition of a threshold on the likelihood ratio statistic used in conjunction with a threshold on the size of a cluster allows the selection of a relevant set of genes. However, even this reduced set of genes will usually be too large for a normal mixture model to be fitted directly to the tissues, and so the use of mixtures of factor analyzers is exploited to reduce effectively the dimension of the feature space of genes. Results: The usefulness of the EMMIX-GENE approach for the clustering of tissue samples is demonstrated on two well-known data sets on colon and leukaemia tissues. For both data sets, relevant subsets of the genes are able to be selected that reveal interesting clusterings of the tissues that are either consistent with the external classification of the tissues or with background and biological knowledge of these sets.

A classification of subantarctic Heard Island vegetation

The vascular and bryophyte floras of subantarctic Heard Island were classified using cluster analysis into six vegetation communities: Open Cushion Carpet, Mossy Feldmark, Wet Mixed Herbfield, Coastal Biotic Vegetation, Saltspray Vegetation, and Closed Cushion Carpet. Multidimensional scaling indicated that the vegetation communities were not well delineated but were continua. Discriminant analysis and a classification tree identified altitude, wind, peat depth, bryophyte cover and extent of bare ground, and particle size as discriminating variables. The combination of small area, glaciation, and harsh climate has resulted in reduced vegetation variety in comparison to those subantarctic islands north of the Antarctic Polar Front Zone. Some of the functional groups and vegetation communities found on warmer subantarctic islands are not present on Heard Island, notably ferns and sedges and fernbrakes and extensive mires, respectively.

Communities of the postindustrial city

The authors discern the community structure of the postindustrial city, with reference to Australia. They focus empirically on three major types of Australian urban center: urban regions. metropolitan areas that are not part of urban regions, and other major cities. These three account for almost three-quarters of the Australian population. The authors draw on a conceptualization formulated by Marcuse and van Kempen to guide the analysis, with a combination of cluster analysis and discriminant analysis being applied to aggregate (essentially census) data to identify the communities. Nine major Australian urban communities are identified-four are affluent. four are disadvantaged. and one is a working-class community. The communities found, however, differed greatly from those cited in the Marcuse and van Kempen schema.

"Owned by...". Country of origin's new cue

This study identifies and explores a new country of origin (COO) cue, “owned by….” The importance of three extrinsic cues “owned by …,” “made in …” and price was examined using conjoint analysis. Data were collected from a sample of 268 undergraduate students familiar with color televisions. Segments were formed using cluster analysis and analyzed using multiple discriminant analysis. “Owned by …” was found to be important and distinct from the “made in …” cue. Segments based on the two COO cues were identified using importance weights and individual utilities. When segments were formed using individual utilities the individual difference construct, economic nationalism, provided discriminatory power while consumer ethnocentrism did not, supporting the hypothesis that economic nationalism and consumer ethnocentrism differ. Practitioners can now use “owned by …” knowing that it forms an important and distinct marketing tool. Limitations and future research are discussed.

Model-based clustering in gene expression microarrays: An application to breast cancer data

In microarray studies, the application of clustering techniques is often used to derive meaningful insights into the data. In the past, hierarchical methods have been the primary clustering tool employed to perform this task. The hierarchical algorithms have been mainly applied heuristically to these cluster analysis problems. Further, a major limitation of these methods is their inability to determine the number of clusters. Thus there is a need for a model-based approach to these. clustering problems. To this end, McLachlan et al. [7] developed a mixture model-based algorithm (EMMIX-GENE) for the clustering of tissue samples. To further investigate the EMMIX-GENE procedure as a model-based -approach, we present a case study involving the application of EMMIX-GENE to the breast cancer data as studied recently in van 't Veer et al. [10]. Our analysis considers the problem of clustering the tissue samples on the basis of the genes which is a non-standard problem because the number of genes greatly exceed the number of tissue samples. We demonstrate how EMMIX-GENE can be useful in reducing the initial set of genes down to a more computationally manageable size. The results from this analysis also emphasise the difficulty associated with the task of separating two tissue groups on the basis of a particular subset of genes. These results also shed light on why supervised methods have such a high misallocation error rate for the breast cancer data.

O servidor p??blico brasileiro: uma tipologia da burocracia

As teorias sobre a burocracia governamental e seu comportamento fornecem diferentes abordagens te??ricas e diferentes interpreta????es. A partir da tipologia de agentes burocr??ticos criada por Anthony Downs (1967), esse trabalho analisa os servidores p??blicos federais brasileiros e sua postura face ao trabalho. Com a aplica????o de question??rios a um grupo de servidores, buscou-se verificar a exist??ncia e/ou pertin??ncia dos tipos descritos como alpinistas, conservadores, defensores, militantes e homens de Estado. Os dados obtidos foram tratados pela t??cnica de an??lise de aglomerados. Os resultados encontrados apontam que a tipologia possui limites fluidos entre um perfil de burocrata e outro, acenando para a necessidade de se repensar as concep????es sobre a burocracia governamental e aprofundar os estudos.

Análise ecológica dos acidentes e da violência letal em Vitória, ES

Objetivo: Analisar o contexto socioeconômico e sua relação com a incidência espacial da mortalidade devido à violência. Métodos: Foi realizado estudo do tipo ecológico no município de Vitória, ES, de 2000 a 2003, sobre a distribuição espacial da mortalidade por acidentes e violência, com base nas informações populacionais e socioeconômicas. Os dados sobre mortalidade foram relacionados a informações como local de residência da vítima, tipo de ocorrência, sexo e raça/cor. A análise das informações utilizou a média espacial, odds ratio e análise de cluster. Resultados: Ocorreram 828 óbitos por violência no período estudado, representando 17% do total de óbitos do município. Destes, 72% eram homicídios, 21,8% acidentes de transporte e 6% suicídios. O padrão das vítimas dos homicídios foi ser jovem, negro, do sexo masculino e residente em regiões mais pobres da cidade. Suicídios e acidentes de transporte acometeram vítimas mais velhas, brancas, do sexo feminino e residentes na área mais rica da cidade. Conclusões: O resultados mostram que a violência é um fenômeno que atinge todas as classes sociais, com destaque para as pessoas da raça negra e baixo nível socieconômico que têm maior chance de morte por homicídio; e brancos de nível socioeconômico mais elevado, suicídios e acidentes de transporte se sobressaem.

Usabilidade e qualidade da informação : avaliação do Portal do aluno da Universidade Federal do Espírito Santo

O presente trabalho tem por objetivo avaliar o Portal do Aluno da Universidade Federal do Espírito Santo, identificando fatores associados à usabilidade que afetam a percepção de qualidade da informação e diferenciando grupos de usuários em função da usabilidade do Portal. Para tanto, foi realizado um levantamento por meio de um questionário aplicado aos usuários, com abordagem predominantemente quantitativa. Foi descrito o perfil dos alunos, o contexto em que utilizam o Portal e qual avaliação fazem dos relatórios e atividades. A partir do modelo elaborado no estudo, no qual a usabilidade contou com seis dimensões (facilidade de aprendizado, facilidade de memorização, eficiência, satisfação, suporte a erros e utilidade), constatou-se que, com exceção da facilidade de aprendizado, as demais dimensões possuem significância estatística na percepção da qualidade da informação, sendo a mais influente a dimensão satisfação. Por meio da análise de conglomerados, foram identificados três grupos, com base nas avaliações dos fatores associados ao atendimento de suas expectativas e aos resultados do uso do portal (satisfação, eficiência e utilidade): o primeiro grupo composto por alunos que avaliaram melhor estes fatores bem como as atividades, os relatórios e a qualidade da informação do Portal; o segundo que avaliaram medianamente; e o terceiro que avaliaram pior. Através da regressão simples utilizando a média das dimensões de usabilidade, verificou-se também que a qualidade da informação está fortemente correlacionada (r=0,7) com a usabilidade do Portal, tendo um poder de predição de 49%. Também foram obtidas respostas acerca do que era mais confuso e sugestões de melhorias que ajudaram a formular, conjuntamente com as demais análises, as propostas do Plano de Intervenção. Embora ainda apresente deficiências, em uma escala de 0 a 5, o Portal foi avaliado acima da média na dimensão satisfação (3,42), bem como obteve média geral de qualidade da informação de 3,31 e de usabilidade de 3,69 . Desta forma, pode-se dizer que ele tem cumprido sua função.

Padrões de uso de habitat do boto-cinza (Sotalia guianensis) na região da foz do rio Doce, costa norte do Espírito Santo, Sudeste do Brasil

Entre março de 2011 e dezembro de 2012 foram realizadas 30 saídas de campo para avaliar os padrões de uso de habitat e estrutura de grupo de Sotalia guianensis na região da foz do rio Doce, costa norte do Espírito Santo. A coleta de dados foi realizada com auxílio de uma embarcação a partir de rotas pré-determinadas distribuídas homogeneamente na área de estudo. Informações sobre as variáveis ambientais foram coletadas a cada hora de amostragem e a cada grupo de golfinhos avistado. Através da análise de Cluster foram identificados três diferentes habitats baseados na similaridade entre variáveis ambientais. Durante 242hs48min de amostragem foram percorridos 1.523km e 119 grupos de botos-cinza foram avistados. Grupos de Sotalia guianensis, assim como indivíduos imaturos, foram observados ao longo de todo o ano na área de estudo, não apresentando diferença sazonal entre as estações seca (abril a setembro) e chuvosa (outubro a março). Os grupos apresentaram uma média de 9,9 indivíduos. Animais imaturos estavam presentes na maioria dos grupos (71%), apresentando uma relação direta com o número de adultos. Os botos-cinza apresentaram o uso quase exclusivo da região marinha aberta adjacente à desembocadura do rio apontando um padrão de uso de habitats heterogêneo, onde as áreas de maior concentração de golfinhos não corresponderam às áreas preferenciais de alimentação. Os resultados obtidos neste trabalho refletem como S. guianensis responde a complexidade dos fatores bióticos e abióticos da área de estudo, apontando um padrão de uso de habitat diferenciado para a espécie.

Tourists’ perceptions of world heritage destinations: the case of Guimarães

Guimarães is a world heritage site (UNESCO) since December 2001, and is hosting the European Capital of Culture (ECOC) in 2012. This paper examines the profile, destination image and motivations of tourists’ visiting Guimarães before the cultural event. Based on survey responses from 276 tourists, this study found that tourists arrived to Guimarães came from the two most important cities in the northern part of Portugal (Porto and Braga). They are relatively young and well educated compared with the average tourists that visited Portugal. The results suggest that many tourists are aware of the city status as a world heritage site encompassing a historic centre, monuments, and architectural buildings. Further, these perceptions shape the image of Guimarães, as the factor analysis indicates that “historical background and functionality” is the most reliable and valid factor behind the choice of visiting the city. Finally, the main tourists’ motivation to choose Guimarães as theirs destination is educational, rather than recreational as they want to live a learning experience.

Tourists’ perceptions of world heritage destinations: The case of Guimarães (Portugal)

Guimara˜es is a UNESCO world heritage site, deemed as such in 2001 and hosted the 2012 European Capital of Culture. This paper examines the profile, destination image, and motivations of tourists’ visiting behaviors in Guimara˜es before the cultural event. Based on survey responses from 276 tourists, we found that tourists arriving in Guimara˜es had previously visited the two most important cities in the northern part of Portugal. These respondents were relatively young and well educated compared to the average tourists that visited Portugal. The results suggest that many tourists were aware of the city status as a world heritage site that encompasses a historic center, monuments, and architectural buildings. Furthermore, these perceptions shape the image of Guimara˜es, as the factor analysis indicates that ‘‘historical background and functionality’’ was the most reliable and valid factor behind the choice of visiting the city.

Chemical, morphological, rheological and thermal properties of Solanum lycocarpum phosphorylated starches

The increasing need for starches with specific characteristics makes it important to study unconventional starches and their modifications in order to meet consumer demands. The aim of this work was to study physicochemical characteristics of native starch and phosphate starch of S. lycocarpum. Native starch was phosphated with sodium tripolyphosphate (5-11%) added with stirring. Chemical composition, morphology, density, binding ability to cold water, swelling power and solubility index, turbidity and syneresis, rheological and calorimetric properties were determined. Phosphorus was not detected in the native sample, but the phosphating process produced modified starches with phosphorus contents of 0.015, 0.092 and 0.397%, with the capacity of absorbing more water, either cold or hot. Rheological data showed the strong influence of phosphorus content on viscosity of phosphate starch, with lower pasting temperature and peak viscosity higher than those of native starch. Enthalpy was negatively correlated with the phosphorus content, requiring 9.7; 8.5; 8.1 and 6.4 kJ g-1 of energy for the transition from the amorphous to the crystalline state for the starch granules with phosphorus contents of 0; 0.015; 0.092 and 0.397%, respectively. Cluster analysis and principal component analysis showed that starches with 0.015 and 0.092% phosphorus have similar characteristics and are different from the others. Our results show that the characteristics of phosphate modified S. lycocarpum starch have optimal conditions to meet the demands of raw materials, which require greater consistency in stickiness, combined with low rates of retrogradation and syneresis.

Influence of strawberry jam color and phenolic compounds on acceptance during storage

The objective of this study was to evaluate the influence of the color and phenolic compounds of strawberry jam on acceptance during storage. Jams were processed, stored for 120 days and evaluated monthly for chromatic characteristics, total phenolic compounds, total anthocyanins (ANT), total ellagic acid (TEA), flavonoids and free ellagic acid (FEA), and sensory acceptance as well. Data were submitted to analysis of variance (ANOVA) and the means were compared by the Least Significant Difference (LSD). Cluster Analysis and Partial Least Square Regression (PLS) were performed to investigate the relationships between instrumental data and acceptance. Contents of ANT, TEA and redness decreased during storage. Other chemical characteristics and sensory acceptance showed a nonlinear behavior. Higher acceptance was observed after 60 days, suggesting a trend of quality improvement followed by decline to the initial levels. The same trend was observed for lightness, non-pigment flavonoids and FEA. According to PLS map, for consumers in cluster 2, acceptance was associated to jams at 60 days and to luminosity, FEA, and non-pigment flavonoids. For cluster 1, a positive association between flavor liking, jam at initial storage, and the contents of TEA and ANT was indicated. Jams at 120 days were positively associated to hue and negatively associated to color liking, for cluster 1. Color and texture were positively correlated to overall liking for cluster 2, whereas for cluster 1, overall acceptance seemed to be more associated to flavor liking. Changes in color and phenolic compounds slightly influenced the acceptance of strawberry jams, but in different ways for consumers clusters.

Corporate social responsibility practices at brazilian firms

Corporate Social Responsibility practices have been on the rise in recent years in firms all over the world. Brazil, as one of the most important countries emerging on the international scene, is no exception to this, with more and more firms taking up these practices. The present study focuses on analyzing the corporate social responsibility practices that Brazilian companies engage into. The sample used is comprised of 500 firms grouped by geographical area; the theoretical framework is based on stakeholder and institutional theories; and the technique used for the analysis is the biplot, more specifically the HJ Biplot and cluster analysis. From the results obtained it is possible to infer that the CSR variables corresponding to environmental practices are more closely linked to companies located in the northern areas of Brazil. Social and community practices are related to companies primarily in the southern and northeastern regions of the country.

Contributo do enoturismo para o desenvolvimento de regiões do interior: o caso da rota dos vinhos do alentejo

The wine industry and its relationship with the tourism sector, as well as with the motivations, characteristics, and behaviors wine tourists are relevant for the valuable creation. Some scholars have identified distinct wine tourism market segments based on a supply-side analysis of certain wine-producing tourism destinations. Subsequent studies used cluster analysis to prove that specific wine tourism market segments can be identified in the Alentejo Wine Route. The significant dimension and economical importance of wine tourism in the Alentejo region point towards the need for more dynamic planning and branding efforts. Such efforts will no doubt place the Alentejo Wine Region on par with some of the foremost wine-producing regions in the world.