Estimación de los resultados en matemáticas y ciencias de las pruebas TIMSS 2015: un nuevo enfoque desde la metodología de áreas pequeñas

Abstract

TIMSS is an internationally applied tool for measuring trends in mathematics and science achievement in the fourth grade of primary school and the eighth grade of secondary school. The design of these tests makes it possible to obtain comprehensible and comparable results, which allow governments of different nations to create, maintain or abandon public policies aimed at improving their education system. Naturally, these tests have become very important at a global level. In view of the above, the objective of this academic work is to propose an estimator using Small Area Estimation, which allows improving the quality of the estimates currently obtained with the sampling design used in TIMSS 2015. In addition, this methodology allows us to estimate the result that would have been obtained by a country that did not administer this test in 2015, but has auxiliary information on academic achievement. The Fay-Herriot model is used to construct the estimator of academic achievement, using auxiliary variables such as demographic and socio-economic information and results obtained in previous administrations of the test. Finally, this paper shows that the use of small area estimation in international tests improves the efficiency of the results obtained and thus allows for better decision-making in educational policy.