Education and Depression: Causal random forest estimation

Göktaş D.

Econometric Research Association 1st International Data Analytics and Machine Learning Conference, Ankara, Türkiye, 28 Haziran 2024 - 28 Nisan 2025, ss.1-4, (Özet Bildiri)

  • Yayın Türü: Bildiri / Özet Bildiri
  • Basıldığı Şehir: Ankara
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.1-4
  • Bilecik Şeyh Edebali Üniversitesi Adresli: Evet

Özet

Health and education levels are both indicators of human capital, and they are also linked. Education is considered one of the most influential factors in the so-called “health – socioeconomic status (SES)” gradient. I apply the gradient for mental health by utilising Türkiye Health Survey 2022.  

This study attempts to estimate depression probabilities to gauge the possible causality between an individual’s educational attainment and having depression by controlling region, cohort effects and social ties for men and women samples. The depression score is determined based on the questions which are consistent with patient health questionnaire (PHQ). This study provides a novel approach to addressing average treatments effects in the education gradient of health. Causal random forest technique is applied to predict depression prevalence. It is expected that education is negatively associated with depression symptoms, indicating a higher level of mental well-being.