The reasons why the Regression Tree Method is more suitable than General Linear Model to analyze complex educational datasets

Abstract

Any quantitative method is shaped by certain rules or assumptions which constitute its own rationale. It is not by chance that these assumptions determine the conditions and constraints which permit the evidence to be constructed. In this article, we argue why the Regression Tree Method’s rationale is more suitable than General Linear Model to analyze complex educational datasets. Furthermore, we apply the CART algorithm of Regression Tree Method and the Multiple Linear Regression in a model with 53 predictors, taking as outcome the students’ scores in reading of the 2011’s edition of the National Exam of Upper Secondary Education (ENEM; N = 3,670,089), which is a complex educational dataset. This empirical comparison illustrates how the Regression Tree Method is better suitable than General Linear Model for furnishing evidence about non-linear relationships, as well as, to deal with nominal variables with many categories and ordinal variables. We conclude that the Regression Tree Method constructs better evidence about the relationships between the predictors and the outcome in complex datasets.

“If I were young…”: Increased Dropout Risk of Older University Students

“…We proceeded to employ a regression tree method to explore relationships between variables without a prior theoretical model (Gomes & Jelihovschi, 2019). Several studies on the use of the tree method with educational data also offer technical arguments that the tree regression method is superior to general linear model techniques for handling data on educational systems that includes 1) nominal variables with many categories; 2) ordinal variables in which the assumption of equal distances between the ranges of values is not very plausible; 3) possible non-linear relationships between predictors and outcome (Gomes & Jelihovski, 2019;Gomes et al, 2020Gomes et al, , 2021.…”

Memorial Para Promoção Docente Ao Cargo De Professor Titular Da Universidade Federal De Minas Gerais, Brazil

“…Realizei tanto estudos aplicados envolvendo análises preditivas em dados educacionais e psicológicos (Gomes, Amantes et al, 2020;Gomes, Fleith, Marinho-Araujo et al, 2020;Pazeto et al, 2019Pazeto et al, , 2020 quanto estudos metodológicos em que investigo as propriedades estatísticas dos métodos de árvore Gomes, Lemos et al, 2020). Ademais, comparei os métodos de árvore com as técnicas mainstream da psicologia e educação Gomes, Lemos et al, 2021) e também propus melhorias para o método (Gomes, Farias, Araujo et al, 2021).…”