Browsing by Author "San Martin Gutiérrez, Ernesto Javier"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    From missing data to informative GPA predictions: Navigating selection process beliefs with the partial identifiability approach
    (John Wiley and Sons Ltd, 2024) Alarcón Bustamante, Eduardo Sebastián; González Burgos, Jorge Andrés; Torres Irribarra, David Esteban; San Martin Gutiérrez, Ernesto Javier
    The extent to which college admissions test scores can forecast college grade point average (GPA) is often evaluated in predictive validity studies using regression analyses. A problem in college admissions processes is that we observe test scores for all the applicants; however, we cannot observe the GPA of applicants who were not selected. The standard solution to tackle this problem has relied upon strong assumptions to identify the exact value of the regression function in the presence of missing data. In this paper, we present an alternative approach based on the theory of partial identifiability that considers a variety of milder assumptions to learn about the regression function. Using a university admissions dataset we illustrate how results can vary as a function of the assumptions that one is willing to make about the selection process.
  • Thumbnail Image
    Item
    Perfiles de creencias sobre prácticas de instrucción matemática de estudiantes de pedagogía de educación Primaria condicionados por la experiencia escolar y la adopción del rol de profesor
    (Universidad Austral de Chile, 2023) Chandía, Eugenio; Huencho, Anahí; San Martin Gutiérrez, Ernesto Javier
    The school itinerary not only has an effect on the learning of mathematics, but also on the beliefs about mathematics, its learning and teaching, and therefore on the construction of teaching models and mathematics instructional practices in future teachers. Thus, this research seeks to identify relationships between the profiles of beliefs about mathematical instructional practices and the formal and informal experience with the role of teacher. For this purpose, a scale of beliefs is constructed and validated in 328 elementary education pedagogy students from 18 training programs in Chile, identifying profiles through latent class analysis and determining relationships using the Chi-square test. The results show that the teaching models experienced by student teachers influence their beliefs, even more so if they have adapted the role of teacher by teaching a classmate or giving private lessons.
  • No Thumbnail Available
    Item
    Perfiles de creencias sobre prácticas de instrucción matemática de estudiantes de pedagogía de educación Primaria condicionados por la experiencia escolar y la adopción del rol de profesor
    (Springer International Publishing, 2023) Chandía, Eugenio; Huencho, Anahí; San Martin Gutiérrez, Ernesto Javier
    The school itinerary not only has an effect on the learning of mathematics, but also on the beliefs about mathematics, its learning and teaching, and therefore on the construction of teaching models and mathematics instructional practices in future teachers. Thus, this research seeks to identify relationships between the profiles of beliefs about mathematical instructional practices and the formal and informal experience with the role of teacher. For this purpose, a scale of beliefs is constructed and validated in 328 elementary education pedagogy students from 18 training programs in Chile, identifying profiles through latent class analysis and determining relationships using the Chi-square test. The results show that the teaching models experienced by student teachers influence their beliefs, even more so if they have adapted the role of teacher by teaching a classmate or giving private lessons.
  • Thumbnail Image
    Item
    The role of identifiability in empirical research
    (2024) San Martin Gutiérrez, Ernesto Javier; Perticará, Marcela; Varas Cáceres, Inés María; Asahi Kodama, Kenzo Javier; González Burgos, Jorge Andrés
    This chapter discusses the general concepts of identification and partial identification of statistical models. We elucidate the identification restrictions to endow with meaning the parameters of interest of the fixed-effects one-parameter logistic model with guessing (1PL-G), a model used in educational measurement. We also review the restrictions for identifying the average treatment effect (ATE) in evaluating a policy or program. To address the fundamental problem of causal inference, we also present a partial identification analysis of the ATE. On the basis of the results, we emphasize the relevance of an identification analysis and the usefulness of considering a partial identification approach in causal inference.