Estimador del valor agregado de las instituciones de educación superior en modelos con error en las variables vía algoritmo EM
| dc.contributor.advisor | Polo González, Mayo Luz | spa |
| dc.contributor.author | Calderón González, Juan Camilo | spa |
| dc.date.accessioned | 2020-12-15T16:12:49Z | spa |
| dc.date.available | 2020-12-15T16:12:49Z | spa |
| dc.date.issued | 2020-12-14 | spa |
| dc.description.abstract | This work is an extension of the methodology proposed by Polo (2018) to estimate the value-added of higher education institutions using mixed hierarchical linear models with error in the variables, where the parameters associated to the model were estimated by maximum likelihood and using the optim function of R. In this work an alternative methodology of estimation of the parameters of the model is developed via EM algorithm and implemented in R through functions that automate the estimation of the value-added of the institutions and the calculation of their standard errors via a bootstrap procedure. This method is applied to engineering, business administration, psychology and humanities students who took the Saber 11 test in the period 2006-2009 and the Saber Pro test in the years 2012 and 2013. Finally, when comparing both methodologies, it is evident that the estimates of the value-added using the EM algorithm are more precise than those obtained using the optim function. | spa |
| dc.description.abstract | Este trabajo es una extensión de la metodología propuesta por Polo (2018) para estimar el valor agregado de las instituciones de educación superior usando modelos lineales jerárquicos mixtos con error en las variables, donde los parámetros asociados al modelo se estimaron por máxima verosimilitud y usando la función optim de R. En este trabajo se desarrolla una metodología alternativa de estimación de los parámetros del modelo vía algoritmo EM y se implementa en R a través de funciones que automatizan la estimación de los valores agregados de las instituciones y el cálculo de sus errores estándar vía bootstrap. Este procedimiento se aplica a estudiantes de Ingeniería, Administración, Psicología y Humanidades que presentaron las pruebas Saber 11 en el periodo 2006-2009 y la prueba Saber Pro en los años 2012 y 2013. Finalmente, al comparar ambas metodologías, se evidencia que las estimaciones del valor agregado usando el algoritmo EM son más precisas que las obtenidas por medio de la función optim. | spa |
| dc.description.degreelevel | Maestría | spa |
| dc.format.extent | 133 | spa |
| dc.format.mimetype | application/pdf | spa |
| dc.identifier.uri | https://repositorio.unal.edu.co/handle/unal/78721 | |
| dc.language.iso | spa | spa |
| dc.publisher.branch | Universidad Nacional de Colombia - Sede Bogotá | spa |
| dc.publisher.department | Departamento de Estadística | spa |
| dc.publisher.program | Bogotá - Ciencias - Maestría en Ciencias - Estadística | spa |
| dc.relation.references | Battauz, M. ; Bellio, R. ; Gori, E.; Covariate measurement error adjustment for multilevel models with application to educational data. Journal of educational and behavioral statistics (2011), p. 283–306 | spa |
| dc.relation.references | Bentler, P. ; Liang, J.; Two-level mean and covariance structures: Maximum likelihood via an EM algorithm. Universidad de California. Departamento de psicología (2011). | spa |
| dc.relation.references | Buonaccursi, J. ; Demidenko, E. ; Tosteson, T.; Estimation in longitudinal random effects models with measurement error. Statistica Sinica (2000), p. 885–903 | spa |
| dc.relation.references | Cui, H. ; Kai, N. ; Zhu, L.; Estimation in mixed effects model with error in variables. Journal of multivariate analysis (2004), p. 53–73 | spa |
| dc.relation.references | Davidian, M. ; Giltinan, D.; Nonlinear models for repeated measurement data. New York: Chapman Hall/CRC (1995) | spa |
| dc.relation.references | Diffey, M. ; Smith, B. ; Welsh, A. ; Cullis, B.; A new REML (parameter expanded) EM algorithm for linear mixed models. En: Australian New Zeland Journal of Statistics. (2017), p. 433–448 | spa |
| dc.relation.references | Dutilleul, P.: The MLE algorithm for the matrix normal distribution. Laboratory of Applied Statistics, Department of Plant Science, Mc Gill University (1999), p. 105–123 | spa |
| dc.relation.references | Goldstein, H. ; Rasbash, J. ; Yang, M.; Adjusting for measurement error in multilevel analysis. Journal of the Royal Statistical Society. Series A (Statistics in Society) (1996), p. 201–212 | spa |
| dc.relation.references | Gonzalez, L.; Notas de clase. Análisis de datos longitudinales. Universidad Nacional de Colombia | spa |
| dc.relation.references | Instituto Colombiano para la Evaluación de la Educación (ICFES): Documentación del examen Saber 11. (2013) | spa |
| dc.relation.references | Instituto Colombiano para la Evaluación de la Educación (ICFES): Documentación del examen Saber Pro. (2013) | spa |
| dc.relation.references | Instituto Colombiano para la Evaluación de la Educación (ICFES): Medición de los efectos de la educación superior en Colombia sobre el aprendizaje estudiantil. (2014) | spa |
| dc.relation.references | Kim, H. ; Lalancette, D.; Literature review on the value-added measurement in higher education. OECD. (2015) | spa |
| dc.relation.references | Laird, N. ; Lange, N. ; Stram, D.: Maximum Likelihood Computation with Repeated Measures: Application of the EM algorithm. Journal of the American Statistical Association (1987), p. 97–105 | spa |
| dc.relation.references | LaMotte, L.; A direct derivation of the REML likelihood function. Statistical papers , p. 321–327 | spa |
| dc.relation.references | Manzi, J. ; SanMartin, E. ; Vellegem, S.; School system evaluation by value added analysis under endogeneity. Psychometrika (2014), p. 130–153 | spa |
| dc.relation.references | Milla, J. ; SanMartin, E. ; Vellegem, S.; Higher Education Value Added Using Multiple Outcomes. Journal of Educational Measurement (2018), p. 368–400 | spa |
| dc.relation.references | Miller, K.; On the inverse of the Sum of Matrices. Mathematical Association of America (1981), p. 67–72 | spa |
| dc.relation.references | Orchard, T. ; Woodbury, M.; A missing information principle: Theory and applications. Proc. of the 6th Symp. on Math. Stat. and Prob (1972), p. 697–715 | spa |
| dc.relation.references | Raudenbush, S. ; Bryk, A.; Hierarchichal Linear Models. Advanced Quantitative Tecniques in the Social Sciences Series | spa |
| dc.relation.references | Raudenbush, W. ; Rowan, B. ; Kang, S.; A multilevel, multivariate model for studying school climate with Estimation via the EM algorithm and application to U.S. High School data. Journal of Educational Statistics (1991) | spa |
| dc.relation.references | Rencher, A.: Methods of Multivariate Analysis. Brigham Young University (2002) | spa |
| dc.relation.references | Rubin, A. ; Laird, N. ; Dempster, A.; Maximum likelihood from incomplete Data via the EM algorithm. Journal of the royal Statistical Society Series B, Methodological (1977), p. 1–38 | spa |
| dc.relation.references | San Martin, E. ; Carrasco, A.: Clasificación de escuelas en la nueva institucionalidad educativa: contribución de modelos de valor agregado para una responsabilización justa. Temas de la agenda pública Centro de Políticas Públicas UC (2012), p. 1–7 | spa |
| dc.relation.references | Televantou, I. ; Marsh, H. ; Kyriakides, L. ; Nagengast, B. ; Fletcher, J. ; Malmberg, L.; Phantom effects in school composition research: consequences of failure to control biases due to measurement error in traditional multilevel models. Routledge Taylor Francis Group (2015), p. 75–101 | spa |
| dc.relation.references | Troncoso, P. ; Pampaka, M. ; Olsen, W.; Beyond traditional school value added models: a multilevel analysis of complex school effects in Chile. Routledge Taylor Francis Group (2015), p. 1–20 | spa |
| dc.relation.references | VanderLeeden, R. ; Busing, F. ; Meijer, E.: Applications of bootstrap methods or two-level models. Multilevel conference (1997) | spa |
| dc.relation.references | Vanegas, L.: Notas de Clase - Modelos Lineales Generalizados. Universidad Nacional de Colombia | spa |
| dc.relation.references | Wilms, D. ; Raudenbush, S.; A longitudinal hierarchichal linear model for estimating school effects and their Stability. Journal of Medical Educational Measurement (1989), p. 209–232 | spa |
| dc.relation.references | Woodhouse, G.; Errors in variables in multilevel models. London: Institute of Education (1996) | spa |
| dc.rights | Derechos reservados - Universidad Nacional de Colombia | spa |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | spa |
| dc.rights.license | Atribución-NoComercial 4.0 Internacional | spa |
| dc.rights.spa | Acceso abierto | spa |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc/4.0/ | spa |
| dc.subject.ddc | 510 - Matemáticas::519 - Probabilidades y matemáticas aplicadas | spa |
| dc.subject.proposal | Value-added | eng |
| dc.subject.proposal | Valor agregado | spa |
| dc.subject.proposal | Algoritmo EM | spa |
| dc.subject.proposal | EM algorithm | eng |
| dc.subject.proposal | Efectividad escolar | spa |
| dc.subject.proposal | School effectiveness | eng |
| dc.subject.proposal | Modelos lineales jerárquicos mixtos | spa |
| dc.subject.proposal | Mixed and hierarchical linear models | eng |
| dc.title | Estimador del valor agregado de las instituciones de educación superior en modelos con error en las variables vía algoritmo EM | spa |
| dc.type | Trabajo de grado - Maestría | spa |
| dc.type.coar | http://purl.org/coar/resource_type/c_bdcc | spa |
| dc.type.coarversion | http://purl.org/coar/version/c_ab4af688f83e57aa | spa |
| dc.type.content | Text | spa |
| dc.type.driver | info:eu-repo/semantics/masterThesis | spa |
| dc.type.version | info:eu-repo/semantics/acceptedVersion | spa |
| oaire.accessrights | http://purl.org/coar/access_right/c_abf2 | spa |

