Dataset regarding access to information for persons with disabilities in Serbia.

Access to information is key for improving the position of persons with disabilities in society. Familiarity with state regulations regarding access to information could be influenced by communication with state authorities concerning the rights of persons with disabilities, especially access to information. Familiarity with these regulations and the specified communication with state authorities might be affected by a number of background variables, such as age and education completed. To clarify relations among these variables, which would enable state authorities and other relevant institutions to define and implement policies that might improve matters, there is a need to prepare and analyze appropriate datasets concerning them. This paper describes such a dataset, preliminary in nature, obtained from answers to part of a questionnaire administered to persons with disabilities living in Serbia. Persons with innate or acquired physical and/or sensory disability were included in the research. This dataset contains raw data of nine variables, as well as analyzed data of ten variables derived from most of the raw data. Besides correlative analyses, the dataset was previously analyzed using PLS (partial least squares) path modeling. To reuse the dataset, a path model with Bayesian estimations may be applied, whose outcomes for different model priors (prior distributions) may be compared to those of the PLS path modeling. The dataset also contains data of two variables that may be included in further research.

Background familiar e desempenho escolar: uma abordagem com variáveis binárias a partir dos resultados do Saresp / Family background and school performance: an approach with binary variables from SARESP results / Fondo familiar y desempeño escolar: Un enfoque con variables binarias a partir de los resultados del SARESP

No presente estudo investiga-se o impacto de fatores externos à escola sobre a escolarização do indivíduo. Renda e escolaridade materna são consideradas para medir o efeito de aspectos familiares no desempenho em matemática do aluno. Para tanto, foram utilizados dados referentes à nota em matemática dos alunos da 3ª série do ensino médio e as respostas dos pais ao questionário socioeconômico, aplicado pelo Sistema de Avaliação do Rendimento Escolar do Estado de São Paulo (Saresp) na edição de 2013. São propostos modelos com variáveis binárias e obtidas estimativas para os parâmetros por meio do software SPSS. Os resultados mostram que rendas mais altas proporcionam melhores desempenhos educacionais, porém há restrições. O nível de escolaridade materna atua positivamente sobre o desempenho do aluno, mas está limitado ao nível adequado de proficiência.

This study researches the impact of outside school factors on individuals' schooling. Income and maternal schooling are taken into consideration when measuring the effect of familiar aspects on students' performance in Mathematics. Therefore, we used data referring to the Mathematics grade of students in 3rd year High School, and the answers provided by their parents for the socioeconomic questionnaire, applied by SARESP in its 2013 edition. Models with binary variables are proposed and estimates for parameters are obtained with SPSS. Results show that students from families with higher incomes indicate better educational performance, but there are restrictions. The level of maternal education positively influences student's performance, but is limited to appropriate proficiency levels.

El presente estudio investiga el impacto de los factores externos a la escuela sobre la escolarización del individuo. Se consideran la renta y la escolaridad materna para medir el efecto de los aspectos familiares en el desempeño del alumno en Matemáticas. Para eso, se utilzaron datos sobre la nota en Matemáticas de los alumnos de la tercera serie de Enseñanza Media y las respuestas de los padres al cuestionario socioeconómico aplicado por la Secretaria da Educação do Estado de São Paulo (SARESP) en la edición de 2013. Se proponen modelos con variables binarias y estimativos para los parámetros que se obtienen con el SPSS. Los resultados muestran que las rentas más altas proporcionan mejores resultados educativos, a pesar de lo cual hay restricciones: el nivel de escolaridad materna actúa positivamente sobre el desempeño del alumno, pero está limitado al nivel adecuado de competencia.

Modern methods for longitudinal data analysis, capabilities, caveats and cautions.

Longitudinal studies are used in mental health research and services studies. The dominant approaches for longitudinal data analysis are the generalized linear mixed-effects models (GLMM) and the weighted generalized estimating equations (WGEE). Although both classes of models have been extensively published and widely applied, differences between and limitations about these methods are not clearly delineated and well documented. Unfortunately, some of the differences and limitations carry significant implications for reporting, comparing and interpreting research findings. In this report, we review both major approaches for longitudinal data analysis and highlight their similarities and major differences. We focus on comparison of the two classes of models in terms of model assumptions, model parameter interpretation, applicability and limitations, using both real and simulated data. We discuss caveats and cautions when applying the two different approaches to real study data.