Browsing by Author "Torres Irribarra, David"

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Big data para la identificación del comportamiento criminal
    (Centro de Políticas Públicas UC, 2019) Wout, Elwin van't; Valenzuela Carvallo, Eduardo; Asahi Kodama, Kenzo Javier; Pieringer Baeza, Christian Philip; Torres Irribarra, David; Larroulet Philippi, Pilar
    El big data ha revolucionado las ciencias y la industria con su impresionante poder de analizar grandes conjuntos de datos y algoritmos que pueden predecir eventos futuros con una alta precisión. Este capítulo estudiará el uso de herramientas automatizadas para identificar el comportamiento delictual, con el objetivo final de ayudar a la policía en su mejora continua de la gestión eficiente de los recursos gubernamentales para reducir la delincuencia. Se han desarrollado modelos matemáticos que permiten extraer información relevante de una base de datos, que contiene registros de detenciones por las policías e información sociodemográfica sobre los victimarios. El análisis descriptivo presenta los indicadores clave del estado actual de delincuencia en Chile y una tipología del comportamiento criminal. La predicción de detenciones futuras es desafiante: la precisión debe aumentarse, antes de usar los algoritmos en la práctica, especialmente porque una predicción errónea puede resultar en costos sociales demasiados altos. Para completar el estudio, se presenta una discusión sobre los alcances y posibles fuentes de sesgo en la predicción. Por último, se elaboran propuestas sobre cómo mejorar las políticas públicas y la organización policial basada en herramientas de big data.
  • Thumbnail Image
    Item
    Continuation Ratio Model for Polytomous Items Under Complex Sampling Design
    (Springer Cham, 2022) Carrasco Ogaz, Diego; Torres Irribarra, David; González Burgos, Jorge Andrés
    The use of polytomous items as part of background or context questionnaires and complex sampling designs are two features common in international large-scale assessments (ILSA). Popular choices to model polytomous items within ILSA include the partial credit model, the graded response model, and confirmatory factor analysis. However, an absent model in ILSA studies is the continuation ratio model. The continuation ratio model is a flexible alternative and a very extendable response model applicable in different situations. Although existing software can fit this model, not all these tools can incorporate complex sampling design features present in ILSA studies. This study aims to illustrate a method to fit a continuation ratio model including complex sampling design information, thus expanding the modelling tools available for secondary users of large-scale assessment studies.
  • Thumbnail Image
    Item
    Continuation ratio model for polytomous responses with censored like latent classes
    (Springer, 2023) Carrasco Ogaz, Diego; Torres Irribarra, David; González Burgos, Jorge Andrés
    Polytomous item responses are prevalent in background or context questionnaires of International large-scale assessments (ILSA). Responses to these types of instruments can vary in their symmetry or skewness. Zero inflation of responses can lead to biased estimates of item parameters in the response model and also to a downward bias in the conditional model when the zero inflated component is not accounted for in the model. In this paper, we propose to use a mixture continuation ratio response model to approximate the non-normality of the latent variable distribution. We use responses to bullying items from an ILSA study, which typically present positive asymmetry. The present model allows us to distinguish bullying victimization risk profiles among students, retrieve bullying victimization risk scores, and determine the population prevalence of the bullying events. This study also aims to illustrate how to fit a mixture continuation ratio model, including complex sampling design, thus expanding the modeling tools available for secondary users of large-scale assessment studies.
  • Thumbnail Image
    Item
    Metacognition, Self-Regulation, and Autonomy Support in the Chilean Mathematics Classroom: An Observational Study
    (2018) Preiss Contreras, David Daniel; Grau Cárdenas, Valeska Valentina; Torres Irribarra, David; Calcagni García, María Elisa
    This paper presents the results of an observational study developed on lessons taught by 128 teachers for a national teaching assessment program in Chile and whose practice was identified as outstanding. Specifically, we studied which strategies teachers used to promote students’ self-regulation and autonomy during segments involving teacher-led public talk, student-led public talk, shared engagement, and private work. Additionally, we examined whether the instructional practices targeting self-regulation that occur throughout these segments can be accounted for based on two overall dimensions of teacher practices, namely one of promotion of metacognition and one of promotion of motivation. During public segments, teachers encouraged student participation; during private work segments, teachers offered clues for problem solving. Thus, there was a stronger focus on motivational regulation instructional strategies during public segments and on metacognitive instructional strategies during private ones. A confirmatory factor analysis supported the hypothesis of two distinctive but related factors behind the observed self-regulation promotion strategies, one motivational, and one cognitive.
  • Thumbnail Image
    Item
    The role of classroom discussion
    (2018) Carrasco Ogaz, Diego Alonso; Torres Irribarra, David; Sandoval-Hernández, Andrés; Isac, Maria Magdalena; Miranda, Daniel