Cristiano Mauro Assis Gomes

Predicting Increased Blood Pressure Using Machine Learning

The present study investigates the prediction of increased blood pressure by body mass index (BMI), waist (WC) and hip circumference (HC), and waist hip ratio (WHR) using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women) from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42), misclassification (.19), and the higher pseudo R 2 (.43). This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25), misclassification (.16), and the higher pseudo R 2 (.46). This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power.

Propriedades psicométricas do conjunto de testes da habilidade visuo espacial

This article analyses the psychometrical properties of a test kit developed to measure visual-spatial ability in terms of its factorial structure, unidimensionality, convergent validity and divergent validity. A sample of 558 students that were either attending High School or had just concluded it participated of this research. The Visualization Test (Vz), Flexibility of Closure Test (CF), Visual Memory Test (MV), Figural Fluency Test (FF), Ideational Fluency Test 1 (FI1) and Ideational Fluency Test 2 (FI2) were used. The data analysis used the exploratory factorial analysis, the confirmatory factorial analysis and the fit to the Rasch model procedures. The model fit indexes are in accordance with the cutoff values suggested by the literature. The tests showed a two-level factorial structure, although it can be taken as an unidimensional structure. The tests converge to measure the visual-spatial ability and diverge to measure the fluency ability which was used in this study as contrast ability.

Validação da Escala de Abordagens de Aprendizagem (EABAP) em uma amostra Brasileira

The main objective of the current study is to build and validate the Learning Approach Scale (LAS), which was developed to assess the deep and surface dimensions in a Brazilian sample. Seven hundred sixteen participants from junior and high schools in the city of Belo Horizonte took part in the research. The exploratory factor analysis was used to identify those dimensions and to select the best items. Only 17 items were kept from the 27 original ones. By the Confirmatory Factor Analysis it was possible to identify the adequacy of one general and two specific factors, the latter representing the deep and surface approaches (χ2=281.50; gl=116; CFI=0.94; GFI=0.95 and RMSEA=0.05). The implications of the results for the theory of approaches and the application of the scale in the Educational Psychology field are discussed.

A articulação entre conhecimento tácito e inovação tecnológica: a função mediadora da educação

Resumen pt: Esta pesquisa, realizada no setor petroquimico brasileiro, analisa o processo de mudanca tecnologica em ambiente de trabalho cujas operacoes demandam ...

Avaliando a avaliação escolar: notas escolares e inteligência fluida

Brazilian education defines through ENEM that teaching must promote development of intelligence (scholar competences). This article discusses the quality of two school evaluations as indicative of these principle. Two studies were performed. The first one analyses 230 student’s data from a federal high school in Belo Horizonte. The second analyses 273 high school student’s data from a private school in Belo Horizonte. The same methods were used in both studies to contrast the results. The relationship between fluid intelligence, grade school and general scholar competence was analyzed, by structural equation modeling. The results show that school evaluation of the two studies has connectivity with the national principles. The implications of the results are analyzed and discussed.Brazilian education defines through ENEM that teaching must promote development of intelligence (scholar competences). This article discusses the quality of two school evaluations as indicative of these principle. Two studies were performed. The first one analyses 230 students data from a federal high school in Belo Horizonte. The second analyses 273 high school students data from a private school in Belo Horizonte. The same methods were used in both studies to contrast the results. The relationship between fluid intelligence, grade school and general scholar competence was analyzed, by structural equation modeling. The results show that school evaluation of the two studies has connectivity with the national principles. The implications of the results are analyzed and discussed.

Rationale and Applicability of Exploratory Structural Equation Modeling (ESEM) in psychoeducational contexts

Background: In last few years, the use of confirmatory factor analysis (CFA) has become dominant in structural validation of psychological tests. However, the requirement of latent variables only loading on specific target items introduces some constraints on the solutions found, namely a factor solution that links some items only in one specific dimension. The most recent use of exploratory structural equation modeling (ESEM), which allows items to be predominantly related to a factor, with non‐zero loadings on other factors, has been identified as the one that best respects the proper functioning of the assessed psychological attributes. Method: In this study we compared the two approaches to structural validity using the answers of a sample of 2,478 first‐year higher education students to a multidimensional questionnaire of academic expectations. Results: The results show clear gains in information collected when combining CFA and ESEM. Conclusions: In conclusion, some implications are highlighted for research and practice of psychological assessment. Resumen Fundamentos y aplicabilidad del Modelado Exploratorio de Ecuaciones Estructurales en contextos psicoeducativos. Antecedentes: en los últimos años, el uso del Análisis Factorial Confirmatorio (AFC) se ha convertido en un tipo de análisis predominante en la validación de tests psicológicos. Sin embargo, el requisito de que las variables latentes únicamente carguen sobre algunas de las respectivas dimensiones de destino conlleva algunas restricciones a las soluciones obtenidas; es decir, una solución factorial que requiere la vinculación de ciertos ítems solo en una dimensión. El uso más reciente del Modelo Exploratorio de Ecuaciones Estructurales (ESEM), que permite que los ítems puedan ser predominantemente relacionados con un factor y con cargas diferentes a cero en otros factores, ha sido identificado como aquel que mejor respeta el buen funcionamiento de los atributos psicológicos evaluados. Método: en este estudio, con las respuestas de una muestra de 2.478 estudiantes de primer año de la enseñanza superior a un cuestionario multidimensional de expectativas académicas, hemos comparado los dos enfoques de validez estructural. Resultados: los resultados muestran claros beneficios en la información recopilada al combinar el AFC y el ESEM. Conclusiones: como conclusión se señalan algunas implicaciones para la investigación y la práctica de evaluación psicológica.

Factor structure of Raven's Coloured Progressive Matrices

This studys objective was to verify the factor structure of Ravens Coloured Progressive Matrices (CPM). The database used included the responses of 1,279 children, 50.2% of which were males with an average age of 8.48 years old and a standard deviation of 1.49 yrs. Confirmatory factor analyses were run to test seven models based on CPM theory and on a Brazilian study addressing the tests structure. The results did not confirm the CPM theoretical proposition concerning the scales but indicated that the test can be interpreted by one general factor and one specific factor or one general factor and three specific factors; both are bi-dimensional models. The three-factor model is, however, more interpretable, suggesting that the factors can be used as a means of screening childrens cognitive developmental stage.O objetivo do trabalho foi verificar a estrutura fatorial das Matrizes Progressivas Coloridas de Raven - MPC. Para isso, utilizou-se um banco de dados contendo as respostas a MPC de 1.279 criancas, 50,2% do sexo masculino, com idade media de 8,48 anos e desvio-padrao de 1,49 anos. Foram efetuadas analises fatoriais confirmatorias testando sete modelos arquitetados a partir da teoria das MPC e de um estudo brasileiro que explorou a estrutura desse teste. Os resultados nao confirmaram a proposta teorica da MPC referente as escalas propostas no teste, mas indicaram que o teste pode ser interpretado por um fator geral e um fator especifico, ou um fator geral e tres especificos, os dois modelos sendo bidimensionais. No entanto, o modelo com tres fatores especificos e mais interpretavel, sugerindo que os fatores podem ser utilizados como screening do estagio de desenvolvimento cognitivo que a crianca se encontra.

Validade incremental da Escala de Abordagens de Aprendizagem (EABAP)

This paper investigates the incremental validity of learning approach in academic achievement. Participants were 684 junior and high school students from a private school in Belo Horizonte, Minas Gerais, Brazil. Intelligence is measured by fluid intelligence items of the Higher-Order Cognitive Factors Kit. Learning approach is measured by the Learning Approaches Scale. Academic achievement is measured by annual grades in Mathematics, Portuguese (native language), Geography, and History. Three hypotheses about the relation among intelligence, learning approach and academic achievement are tested through structural equation modeling. The direct relation model was the most adequate and showed good fit. Intelligence and learning approach show direct effect in academic achievement. Learning approach has incremental validity of individual differences in academic achievement, independently of intelligence.

Relações hierárquicas entre os traços amplos do Big Five

The Big Five model sustains that human personality is composed by dozens of specific factors. Despite of diversity, specific factors are integrated in five broad traits that are in the same hierarchical level. The current study presents an alternative hypothesis arguing that there are hierarchical levels between the broad traits of the model. Six hundred and eighty-four junior and high school level students from 10 to 18 years old (M = 13.71 and SD= 2.11) of a private school in the city of Belo Horizonte, Minas Gerais, Brazil participated in the study. The Big Five was measured by an Inventory of Personality Traits, initially named as Personality Adjective Inventory, elaborated by Pinheiro, Gomes and Braga (2009). This instrument measures eight polarities of the ten presented in the Big Five Model. Two models were compared through path analysis: a four-level hierarchical model and a non-hierarchical one. The hierarchical model showed adequate data fit, pointing to its superiority in relation to the non-hierarchical model, which did not present it. Implications to the Big Five Model are discussed.

Validação das propriedades psicométricas do RESTQ-Coach na versão brasileira

The purpose of this study was to validate a Brazilian version of the The Recovery, Stress Questionnaire for Coaches (RESTQ-Coach), herein named Questionario de Estresse e Recuperacao para Treinadores Esportivos (RESTQ-Coach-versao brasileira). The RESTQ is an assessment tool for Brazilian sport coaches. Also, using Confirmatory Factor Analysis (CFA) and Exploratory Factor Analysis (EFA), the purpose of this study was to verify the adequacy of the theoretical model by Kallus e Kellmann (1993). A sample comprised of 424 coaches, average age of 37.06 (±9.20) years, was divided into eleven different sports modalities, consisting of five team sports and six individual sports. The results of the AFC shows that the original model of the questionnaire proposed by Kallus e Kellmann (1993) is inadequate for this sample, and that the AFE was identified as the best solution to a factorial validation of the instrument, which is composed of six factors. This solution disclosed general internal consistency values of α = .85. Values of the global adjustment indicators of the Brazilian model for six AFE factors were: χ2 = 9.660,239 e gl = 2695, p=0,001; CFI= 0,96; TLI= 0,95; RMSEA 0,07, expressing their quality. We concluded that Kallus e Kellmann (1993) model was not corroborated by the AFC for this Brazilian sample. The best factorial solution to the RESTQ-Coach Brazilian version is composed by six constructs.