Inferencia causal en investigación educativa: Análisis de la causalidad en estudios observacionales de carácter transversal

Fernando Martínez-Abad; Jaime León

doi:10.30827/relieve.v29i2.26843

Autores

Fernando Martínez-Abad University of Salamanca, Spain https://orcid.org/0000-0002-1783-8198
Jaime León University of Las Palmas de Gran Canaria, Spain https://orcid.org/0000-0002-9587-4047

DOI:

https://doi.org/10.30827/relieve.v29i2.26843

Palavras-chave:

Análise causal, metodologia estatística, avaliação, análise de dados

Resumo

A assunção de relações de causa-efeito na investigação ex post facto é um problema amplamente conhecido no domínio da metodologia de investigação em ciências sociais. Para fazer face a esta importante limitação, a utilização de técnicas de inferência causal, um conjunto de procedimentos estatísticos estabelecidos para poder tirar conclusões causais em investigações não experimentais, tem vindo a generalizar-se nos últimos anos. Apesar da sua grande popularidade e disseminação no âmbito das ciências sociais e da saúde, a sua utilização em investigação educativa é ainda marginal. Assim, este documento introduz as principais técnicas de inferência causal disponíveis para o investigador educativo quando existem dados observacionais de painel. Depois de discutir as principais características e o potencial das técnicas de correspondência por pontuação de propensão, variáveis instrumentais e conceção de regressão descontínua, apresenta-se um exemplo da aplicação de cada uma delas utilizando as bases de dados obtidas na avaliação PISA 2018. A competência matemática é incluída como variável dependente em todos os modelos propostos. Dadas as diferentes características de cada uma destas técnicas, a variável independente utilizada varia nos três modelos aplicados: assistência ao ensino infantil na correspondência por pontuação de propensão, expectativas académicas do estudante em variáveis instrumentais e dimensão do município em que a escola se localiza em conceção de regressão descontínua. O artigo conclui discutindo o potencial deste conjunto de técnicas, tendo em conta as necessidades e os procedimentos metodológicos mais comummente aplicados na investigação educativa.

Downloads

Não há dados estatísticos.

Biografia do Autor

Fernando Martínez-Abad, University of Salamanca, Spain

Associate Professor in the Area of Research Methods and Diagnosis in Education at the University of Salamanca and Associate Director of the Master's Degree in Evaluation and Research in Learning Organizations and Contexts (MEVINAP). His teaching profile focuses on the field of research methodology in education and quantitative data analysis. His main lines of research deal with factors associated with academic achievement and the analysis of educative large-scale international assessments: school effectiveness and educational equity. (email: fma@usal.es)

Jaime León, University of Las Palmas de Gran Canaria, Spain

Professor of Research Methods in Education at the University of Las Palmas de Gran Canaria. His concern as a professor is that primary and secondary teachers get to optimize their students learning, for this he focuses on evidence-based education. As a researcher his concern is the same, to optimize the learning and performance of students, especially in secondary. To do so, he focuses on identifying factors that can be modified: teaching quality, classroom language, passion for knowledge, etc. In order to get the teacher to change in the classroom, he is focusing on designing a method that allows the teacher to obtain feedback on his or her teaching practice. Some of his publications and projects can be consulted in jaimeleon.es/ULPGC (email: jaime.leon@ulpgc.es).

Referências

Ali, M. S., Groenwold, R. H. H., Pestman, W. R., Belitser, S. V., Roes, K. C. B., Hoes, A. W., de Boer, A., & Klungel, O. H. (2014). Propensity score balance measures in pharmacoepidemiology: A simulation study. Pharmacoepidemiology and Drug Safety, 23(8), 802-811. https://doi.org/10.1002/pds.3574

Altman, M. (2020). A more scientific approach to applied economics: Reconstructing statistical, analytical significance, and correlation analysis. Economic Analysis and Policy, 66, 315-324. https://doi.org/10.1016/j.eap.2020.05.006

Amadon, S., Gormley, W. T., Claessens, A., Magnuson, K., Hummel-Price, D., & Romm, K. (2022). Does early childhood education help to improve high school outcomes? Results from Tulsa. Child Development, 93(4), e379-e395. https://doi.org/10.1111/cdev.13752Amini, C., & Nivorozhkin, E. (2015). The urban–rural divide in educational outcomes: Evidence from Russia. International Journal of Educational Development, 44, 118-133. https://doi.org/10.1016/j.ijedudev.2015.07.006

Angrist, J. D., Imbens, G. W., & Rubin, D. B. (1996). Identification of causal effects using instrumental variables. Journal of the American Statistical Association, 91(434), 444-455. https://doi.org/10.1080/01621459.1996.10476902

Antonakis, J., Bendahan, S., Jacquart, P., & Lalive, R. (2010). On making causal claims: A review and recommendations. The Leadership Quarterly, 21(6), 1086-1120. https://doi.org/10.1016/j.leaqua.2010.10.010

Austin, P. C. (2011). Comparing paired vs non-paired statistical methods of analyses when making inferences about absolute risk reductions in propensity-score matched samples. Statistics in Medicine, 30(11), 1292-1301. https://doi.org/10.1002/sim.4200

Barnett, W. S. (1998). Long-Term Cognitive and Academic Effects of Early Childhood Education on Children in Poverty. Preventive Medicine, 27(2), 204-207. https://doi.org/10.1006/pmed.1998.0275

Barnett, W. S., & Jung, K. (2021). Effects of New Jersey’s Abbott preschool program on children’s achievement, grade retention, and special education through tenth grade. Early Childhood Research Quarterly, 56, 248-259. https://doi.org/10.1016/j.ecresq.2021.04.001

Belitser, S. V., Martens, E. P., Pestman, W. R., Groenwold, R. H. H., de Boer, A., & Klungel, O. H. (2011). Measuring balance and model selection in propensity score methods. Pharmacoepidemiology and Drug Safety, 20(11), 1115-1129. https://doi.org/10.1002/pds.2188

Campbell, D. T., & Stanley, J. (1963). Experimental and quasi-experimental designs for research. Wadsworth Publishing.

Castro Aristizabal, G., Giménez, G., & Pérez Ximénez-De-Embún, D. (2017). Educational inequalities in latin america, PISA 2012: Causes of differences in school performance between public and private schools. Revista de Educación, 2017(376), 33-59. Scopus. https://doi.org/10.4438/1988-592X-RE-2017-376-343

Choi, A., Calero, J., & Escardíbul, J.-O. (2012). Private tutoring and academic achievement in Korea: An approach through PISA-2006. KEDI Journal of Educational Policy, 9(2), 299-322. Scopus.

Cinelli, C., Forney, A., & Pearl, J. (2022). A crash course in good and bad controls. Sociological Methods & Research, 00491241221099552. https://doi.org/10.1177/00491241221099552

Cordero, J. M., & Gil-Izquierdo, M. (2018). The effect of teaching strategies on student achievement: An analysis using TALIS-PISA-link. Journal of Policy Modeling, 40(6), 1313-1331. Scopus. https://doi.org/10.1016/j.jpolmod.2018.04.003

Courtney, J. R., Garcia, J. T., Rowberry, J., Eckberg, N., Dinces, S. M., Lobaugh, C. S., & Tolman, R. T. (2023). Measuring impact of New Mexico prekindergarten on standardized test scores and high school graduation using propensity score matching. International Journal of Child Care and Education Policy, 17(1), 9. https://doi.org/10.1186/s40723-023-00112-9

Crespo-Cebada, E., Pedraja-Chaparro, F., & Santín, D. (2014). Does school ownership matter? An unbiased efficiency comparison for regions of Spain. Journal of Productivity Analysis, 41(1), 153-172. Scopus. https://doi.org/10.1007/s11123-013-0338-y

Gamazo, A., & Martínez-Abad, F. (2020). An Exploration of Factors Linked to Academic Performance in PISA 2018 Through Data Mining Techniques. Frontiers in Psychology, 11. https://doi.org/10.3389/fpsyg.2020.575167

García-Pérez, J.I., & Hidalgo-Hidalgo, M. (2017). No student left behind? Evidence from the Programme for School Guidance in Spain. Economics of Education Review, 60, 97-111. Scopus. https://doi.org/10.1016/j.econedurev.2017.08.006

Hill, A. D., Johnson, S. G., Greco, L. M., O’Boyle, E. H., & Walter, S. L. (2021). Endogeneity: A Review and agenda for the methodology-practice divide affecting micro and macro research. Journal of Management, 47(1), 105-143. https://doi.org/10.1177/0149206320960533

Huenermund, P., Louw, B., & Rönkkö, M. (2022). The choice of control variables: How causal graphs can inform the decision. Academy of Management Proceedings, 2022(1), 15534. https://doi.org/10.5465/AMBPP.2022.294

Imai, K., Keele, L., Tingley, D., & Yamamoto, T. (2011). Unpacking the black box of causality: Learning about causal mechanisms from experimental and observational studies. American Political Science Review, 105(4), 765-789. https://doi.org/10.1017/S0003055411000414

Imbens, G. W., & Kalyanaraman, K. (2012). Optimal bandwidth choice for the regression discontinuity estimator. Review of Economic Studies, 79(3), 933-959. Scopus. https://doi.org/10.1093/restud/rdr043

Imbens, G. W., & Lemieux, T. (2008). Regression discontinuity designs: A guide to practice. Journal of Econometrics, 142(2), 615-635. Scopus. https://doi.org/10.1016/j.jeconom.2007.05.001

Imbens, G. W., & Rubin, D. B. (2015). Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction.

Jin, S. (2022). On inconsistency of the overidentification test for the model-implied instrumental variable approach. Structural Equation Modeling. Scopus. https://doi.org/10.1080/10705511.2022.2122978

Kaplan, D. (2016). Causal inference with large-scale assessments in education from a Bayesian perspective: A review and synthesis. Large-Scale Assessments in Education, 4(1). Scopus. https://doi.org/10.1186/s40536-016-0022-6

Kerlinger, F. N., & Lee, H. (1999). Foundations of behavioral research (004 ed.). Wadsworth Publishing.

Lee, D. S., & Lemieux, T. (2010). Regression discontinuity designs in economics. Journal of Economic Literature, 48(2), 281-355. Scopus. https://doi.org/10.1257/jel.48.2.281

Levi, U., Einav, M., Ziv, O., Raskind, I., & Margalit, M. (2014). Academic expectations and actual achievements: The roles of hope and effort. European Journal of Psychology of Education, 29(3), 367-386. https://doi.org/10.1007/s10212-013-0203-4

Lopez-Agudo, L. A., González-Betancor, S. M., & Marcenaro-Gutierrez, O. D. (2021). Language at home and academic performance: The case of Spain. Economic Analysis and Policy, 69, 16-33. Scopus. https://doi.org/10.1016/j.eap.2020.11.003

Maydeu-Olivares, A., Shi, D., & Fairchild, A. J. (2020). Estimating causal effects in linear regression models with observational data: The instrumental variables regression model. Psychological Methods, 25(2), 243-258. https://doi.org/10.1037/met0000226

Martínez-Abad, F., Gamazo, A., & Rodríguez-Conde, M.-J. (2020). Educational Data Mining: Identification of factors associated with school effectiveness in PISA assessment. Studies in Educational Evaluation, 66, 100875. https://doi.org/10.1016/j.stueduc.2020.100875

McCoy, D. C., Yoshikawa, H., Ziol-Guest, K. M., Duncan, G. J., Schindler, H. S., Magnuson, K., Yang, R., Koepp, A., & Shonkoff, J. P. (2017). Impacts of Early Childhood Education on Medium- and Long-Term Educational Outcomes. Educational Researcher, 46(8), 474-487. https://doi.org/10.3102/0013189X17737739

McCrary, J. (2008). Manipulation of the running variable in the regression discontinuity design: A density test. Journal of Econometrics, 142(2), 698-714. https://doi.org/10.1016/j.jeconom.2007.05.005

OECD. (2009). PISA Data Analysis Manual: SPSS, Second Edition. Organisation for Economic Co-operation and Development. https://doi.org/10.1787/19963777

OECD. (2019). PISA 2018 Assessment and Analytical Framework. OECD Publishing. https://doi.org/10.1787/b25efab8-en

Pearl, J., & Mackenzie, D. (2018). The book of why: The new science of cause and effect. Falta editorial

Pokropek, A. (2016). Introduction to instrumental variables and their application to large-scale assessment data. Large-Scale Assessments in Education, 4(1). https://doi.org/10.1186/s40536-016-0018-2

Rosenbaum, P. R., & Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1), 41-55. https://doi.org/10.2307/2335942

Rosenbaum, P. R., & Rubin, D. B. (2022). Propensity scores in the design of observational studies for causal effects. Biometrika, asac054. https://doi.org/10.1093/biomet/asac054

Rubin, D. B. (1974). Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology, 66, 688-701. https://doi.org/10.1037/h0037350

Rutkowski, D., & Delandshere, G. (2016). Causal inferences with large scale assessment data: Using a validity framework. Large-scale Assessments in Education, 4(1), 6. https://doi.org/10.1186/s40536-016-0019-1

Sanders, C. E., Field, T. M., & Diego, M. A. (2001). Adolescents’ academic expectations and achievement. Adolescence, 36(144), 795-802.

Song, Q., & Tan, C. Y. (2022). The association between family socioeconomic status and urban–rural and high-school attainment gaps: A logistic regression analysis of the China Family Panel Studies data. British Educational Research Journal, 48(6), 1102-1124. https://doi.org/10.1002/berj.3817

Stock, J., & Yogo, M. (2005). Testing for weak instruments in linear iv regression. En D. W. K. Andrews, Identification and Inference for Econometric Models (pp. 80-108). Cambridge University Press.

Suárez-Álvarez, J., Fernández-Alonso, R., & Muñiz, J. (2014). Self-concept, motivation, expectations, and socioeconomic level as predictors of academic performance in mathematics. Learning and Individual Differences, 30, 118-123. https://doi.org/10.1016/j.lindif.2013.10.019

Wooldridge, J. M. (2010). Econometric analysis of cross section and panel data, second edition. Revisar

Zhang, Z., Kim, H. J., Lonjon, G., & Zhu, Y. (2019). Balance diagnostics after propensity score matching. Annals of Translational Medicine, 7(1), 16. https://doi.org/10.21037/atm.2018.12.10