Machine learning and propensity score matching for evaluating the effect of special education services on childrens later math performances

Abstract

Listen

Translate article

The goal of the research is to analyze the effect of special education service brought to childrens later math performance. The dataset is derived from Early Childhood Longitudinal Studies(ECLS) program and the children being studied come from diverse socioeconomic and racial/ethnic backgrounds. We applied PSM and modern machine learning methods including OLS, KNN, BART and MLP on the data in order to calculate the average treatment effect of special education services. It turned out that all the listed machine learning algorithms with comparatively low STD outperformed the traditional propensity score matching. KNN, BART and OLS excelled, offering much more stable calculations. The value of ATE computed through all the methods appeared below zero. By applying linear regression and PCA on all the influencing factors, the analysis revealed that the differences of some factors between the controlled and exposed groups led better math performances to appear usually in the absence of special treatment. Thus, special treatment effect led the trained model to predict lower scores, which finally caused the difference to be negative.