4 resultados para Multiple regression
em Repositório Científico da Universidade de Évora - Portugal
Resumo:
In a previous survey of otters ( Lutra lutra L. 1758) in Spain, different causes were invoked to explain the frequency of the species in each province. To find common causes of the distribution of the otter in Spain, we recorded a number of spatial, environmental and human variables in each Spanish province. We then performed a stepwise linear multiple regression of the proportion of positive sites of otter in the Spanish provinces separately on each of the three groups of variables. Geographic longitude, January air humidity, soil permeability and highway density were the variables selected. A linear regression of the proportion of otter presence on these variables explained 62.4% of the variance. We then used the selected variables in a partial regression analysis to specify which proportions of the variation are explained exclusively by spatial, environmental and human factors, and which proportions are attributable to interactions between these components. Pure environmental effects accounted for only 5.5% of the variation, while pure spatial and pure human effects explained 18% and 9.7%, respectively. Shared variation among the components totalled 29.2%, of which 10.9% was explained by the interaction between environmental and spatial factors. Human factors explained globally less variance than spatial and environmental ones, but the pure human influence was higher than the pure environmental one. We concluded that most of the variation in the proportion of occurrences of otter in Spanish provinces is spatially structured, and that environmental factors have more influence on otter presence than human ones; however, the human influence on otter distribution is less structured in space, and thus can be more disruptive. This effect of large infrastructures on wild populations must be taken into account when planning large-scale conservation policies
Resumo:
Pretendemos estudar quais os traços desadaptativos de personalidade que se relacionam com os sintomas depressivos, a afectividade positiva e negativa, numa amostra de 187 estudantes universitários, entre os 18 e os 43 anos. Calculámos as correlações entre as escalas de padrões de personalidade e as escalas de padrões graves de personalidade do Inventário Multiaxial clínico de Millon II (MCMI-II) com os sintomas depressivos avaliados pela Escala de Depressão do Centro de Estudos Epidemiológicos e com a afectividade positiva e negativa avaliadas pela Escala de Afectividade Positiva e Afectividade Negativa. Realizámos uma análise da regressão múltipla utilizando as escalas de padrões de personalidade do MCMI-II como predictores e o resultado na CES-O, como variável dependente. Obtivemos uma correlação significativa entre os padrões de personalidade borderline, masoquista, esquizotípico, negativista e evitante e paranóide e os sintomas depressivos. A afectividade negativa apresenta-se também positivamente correlacionada com os padrões dependente e esquizóide. A afectividade positiva correlacionou-se significativa e positivamente com os padrões histriónico e narcisista e negativamente com os padrões esquizóide, esquizotípico, negativista, borderline, evitante e masoquista. Na análise de regressão, o padrão borderline prevê a presença de sintomas depressivos e os padrões sádico e dependente também, mas num sentido negativo. /ABSTRACT: We intendend to study wich personality traits relate to depressiva symptoms, and positive and negative affectivity, in a sample of 187 university students, between 18 and 43 years. We did the correlation between the personality patterns scales and the personality patterns of severe personality with the depressive symptoms measured by the Center for Epidemiologic Studies Depression Scale and the positive and negative affectivity measured by the Positive Affect and Negative Affect Shedule. We did a multiple regression analysis using the personality patterns scale of Millon Clinical Multiaxial lnventory (MCMI-II) as predictors and the result of CES-D, as dependent variable. We obtained a significant correlation between the borderline, masochist, schizotypal, negativistic, avoidant and paranoid personality patterns and the depressive symptoms. Negative affectivity relates also positively with dependent and schizoid patterns. Positive affectivity correlated significant and positively with histrionic and narcissistic personality patterns and negatively with schizoid, schizotypal, negativistic, borderline, avoidant and masochist personality patterns. ln the regression analysis, the borderline pattern predicts the presence of depressive symptoms as well as the sadistic and dependent, but in the negative sense.
Resumo:
O objetivo desta investigação é testar o contributo das necessidades interpessoais - os sentimentos de não pertença e a perceção de ser um fardo – para o risco de suicídio, avaliado através da ideação suicida. Também se pretende investigar a possível interação entre as necessidades interpessoais e respetivos efeitos quadráticos, controlando o impacto de um conjunto de variáveis que apresentam, muitas vezes, uma correlação significativa com a ideação suicida. Neste estudo participaram 80 utentes idosos em recuperação de uma doença aguda. De acordo com os resultados, os sentimentos de não pertença e a perceção de ser um fardo correlacionam-se com a ideação suicida. No entanto, quando numa análise da regressão múltipla se considera simultaneamente o efeito de ambas as variáveis, apenas os sentimentos de não pertença contribuem significativamente na previsão da ideação suicida. Não se verificaram efeitos de interação nem efeitos quadráticos entre as variáveis necessidades interpessoais; Abstract: “Interpersonal needs and suicide risk in a sample of elderly patients” The aim of this study is to test the contribution of interpersonal needs - thwarted belongingness and perceived burdensomeness - to the risk of suicide, assessed by the presence of suicidal ideation. It also intends to investigate the possible interaction between interpersonal needs and the respective quadratic effects, by controlling the impact of a set of variables which have, many times, a significant correlation with suicidal ideation. In this study participated 80 elderly patients recovering from an acute medical condition. According to the results, thwarted belongingness and perceived burdensomeness are correlated with suicidal ideation. However, when in a multiple regression analysis we considerate simultaneously the effect of both variables, only thwarted belongingness contributes significatively to suicide ideation prediction. No interactions effects or quadratic effects were observed between interpersonal needs variables.
Resumo:
Organizational Cooperation (OC) is a current concept that responds to the growing interdependence among individuals and teams. Likewise, Knowledge Management (KM) accompanies specialization in all sectors of human activity. Most KM processes are cooperation-intensive, and the way both constructs relate to each other is relevant in understanding organizations and promoting performance. The present paper focuses on that relationship. The Organizational Cooperation Questionnaire (ORCOQ) and the Short form of the Knowledge Management Questionnaire (KMQ-SF) were applied to 639 members of research and development (R&D) organizations (Universities and Research Institutes). Descriptive, correlational, linear multiple regression and multivariate multiple regression analyses were performed. Results showed significant positive relationships between the ORCOQ and all the KMQ-SF dimensions. The prediction of KMQ-SF showed a large effect size (R2 = 62%). These findings will impact on how KM and OC are seen, and will be a step forward in the development of this field.