Smoking behaviour is influenced by various psychological and lifestyle factors, including anxiety, distress, and sleep patterns. Understanding these determinants can help in designing effective intervention strategies for smoking cessation among students. This study aims to assess the relationship between smoking behaviour and key lifestyle factors such as anxiety quotient, distress score, and sleep patterns among students. The study also explores the effectiveness of predictive modeling using statistical techniques. Primary data was collected from 203 students enrolled in different courses through a structured questionnaire with uniform scoring criteria. Statistical analysis was performed using logistic regression to examine the association between smoking and selected lifestyle factors. The findings indicate that anxiety quotient, distress levels, and sleep patterns play a crucial role in determining smoking habits among students. Logistic regression results highlight statistically significant associations between these variables and smoking behaviour, while machine learning models provide a robust predictive framework with high classification accuracy. This study demonstrates that lifestyle and mental health factors significantly influence smoking behaviour among students. The use of machine learning techniques enhances predictive capabilities, providing valuable insights for targeted smoking prevention and intervention programs.
Chaudhuri et al. (Tue,) studied this question.