Simple Regression Analysis in Public Health

This module introduces simple regression methods, covering four different types of regression and their commonalities. It focuses on simple linear regression with binary, categorical, and continuous predictors, including model estimation, uncertainty handling, and measuring linear associations.

This module explores logistic regression with binary, categorical, and continuous predictors. It covers confidence intervals, p-values, risk estimation, and interpretation of logistic regression results. Students learn to account for uncertainty in estimates and analyze real-world examples.

This module focuses on Cox regression with different types of predictors. Topics include model estimation, uncertainty handling, survival curve estimation, and interpretation of Cox regression results using real-world examples.

This module covers confounding and adjustment in statistical analysis, including unadjusted and adjusted association estimates. It explores effect modification through various examples and demonstrates the differences between confounding and effect modification.

In this final module, students apply their knowledge as biostatistical consultants for two real-world studies involving injectable contraception and medical appointment scheduling. Students analyze and interpret published results to inform study planning.