Off-campus Michigan Tech users: To download campus access theses or dissertations, please use the following button to log in with your Michigan Tech ID and password: log in to proxy server

Non-Michigan Tech users: Please talk to your librarian about requesting this thesis or dissertation through interlibrary loan.

Date of Award


Document Type

Campus Access Master's Report

Degree Name

Master of Science in Statistics (MS)

Administrative Home Department

Department of Mathematical Sciences

Advisor 1

Xiao Zhang

Committee Member 1

Qiuying Sha

Committee Member 2

Kui Zhang

Committee Member 3

Hairong Wei


This study investigated the dynamics of marijuana consumption patterns over time, utilizing data from the Health and Retirement Study (HRS) spanning from 2012 to 2018. Statistical methodologies such as linear mixed-effects models (LMMs) and generalized estimation equations (GEE) were employed to explore the impact of gender, age, smoking habits, and alcohol consumption on marijuana use.

The analysis revealed significant relationships: gender displayed a positive association with marijuana usage, indicating that males tended to have higher levels of marijuana consumption compared to females. Conversely, age demonstrated a negative relationship with marijuana use, suggesting that older individuals tended to use less marijuana than younger ones. Smoking habits exhibited an inverse relationship with marijuana use, implying that as smoking increased, marijuana usage tended to decrease. In contrast, alcohol consumption showed a positive relationship with marijuana use, indicating that individuals who consumed more alcohol also tended to use more marijuana.

Furthermore, interactions between age and gender, smoking habits, and alcohol consumption significantly influenced marijuana usage trends over time. These findings underscored the necessity of tailored interventions based on gender, age, and substance use for the formulation of effective public health strategies.

Despite the valuable insights provided, the study acknowledged limitations such as reliance on existing data and linear model assumptions. Future research endeavors should prioritize refining methodologies to gain a deeper understanding of marijuana consumption patterns across diverse demographic cohorts, including comprehensive investigations into female-to-male-specific dynamics.