Home > Learning > BI/DS Tutorials and Workshops > 2026 Summer Workshops > 2026 Biostatistics Week 1
Embedded Files
SC INBRE Biostatistics Summer Courses 2026:
Week 2 – Statistical Modeling
Three one-week courses were offered. Four hours/day – 10 am to 12 pm (lecture and discussion) and 1 to 3 pm (R lab and application). Morning sessions and course lab instructions were recorded.
Course Presenter: Dr. Alexander McLain, University of South Carolina Arnold School of Public Health, Professor of Epidemiology and Biostatistics
Courses
Week 1 (June 1-5): Foundations of Data Science in R
Week 2 (June 8-12): Statistical Modeling
Week 3 (June 15-19): Bioinformatics & High-Dimensional Data
Daily Schedule
10 am to 12 pm: Lecture and discussion
1 to 3 pm: R Lab and application
Links
WEEK 2 (June 8-12): Statistical Modeling
Target: Applied regression methods for quantitative, binary, time-to-event, and clustered outcomes.
Monday, June 8, Day 6
MORNING
Simple and Multiple Linear Regression
Model formulation; OLS estimation; interpretation of coefficients; assumptions; R² and model fit; introduction to confounding.
AFTERNOON
Linear Regression Lab
Fitting lm() models; diagnostic plots (residuals, Q-Q, leverage); testing assumptions; applying to a quantitative biological trait.
Tuesday, June 9, Day 7
MORNING
Model Selection and Variable Importance
Overfitting and bias-variance tradeoff; AIC/BIC; stepwise selection (and its limitations); introduction to cross-validation.
AFTERNOON
Model Selection Lab
Comparing nested models; using step() and AIC; k-fold cross-validation with caret or rsample; interpreting results critically.
Wednesday, June 10, Day 8
MORNING
Logistic Regression and Binary Outcomes
Generalized linear models; logit link; odds ratios and their interpretation; model diagnostics; introduction to classification metrics.
AFTERNOON
Logistic Regression Lab
Fitting glm() for case-control data; computing and plotting ROC curves (pROC); evaluating sensitivity/specificity; applying to a disease outcome dataset.
Thursday, June 11, Day 9
MORNING
Survival Analysis
Censoring and time-to-event data; Kaplan-Meier estimator; log-rank test; Cox proportional hazards model; checking the PH assumption.
AFTERNOON
Survival Analysis Lab
KM curves with survminer; log-rank tests; fitting coxph(); visualizing hazard ratios; applying to a clinical or ecological dataset.
Friday, June 12, Day 10
MORNING
Mixed Models and Clustered/Repeated Data
Why standard regression fails with clustered data; random intercepts and slopes; fixed vs. random effects; model interpretation; ICC.
AFTERNOON
Mixed Models Lab
Fitting lme4::lmer() and glmer(); random effect structures; model comparison; applying to longitudinal biological data.
Page updated June 12, 2026
Page updated
Google Sites
Report abuse