R Programming for Infectious Disease Modeling
Meeting Times:
- Monday, July 14, 9:00 AM – 5:00 PM
- Tuesday July 15, 9:00 AM – 5:00 PM
- Wednesday July 16, 9:00 AM – 12:00 PM
Classroom: TBA
Module Summary:
This module aims to enhance R programming skills to prepare participants for advanced mechanistic and statistical infectious disease modeling. It employs an inquiry-based learning approach, using foundational infectious disease modeling tasks—such as writing and solving ordinary differential equations (ODEs) or optimizing functions—as a basis for identifying and teaching essential R programming skills.
Hands-on use of R is a major component of this module; users require a laptop and will use it in all sessions. Examples and exercises will use data drawn from biological and medical applications, including infectious diseases and genetics. Participants require a laptop and will use it in all sessions. Suggested pairing: All later modules.
Prerequisites:
Participants are expected to have a basic understanding of R, including how to open and write R scripts, read in data, and use basic functions and syntax. Participants are also expected to have prior knowledge of basic descriptive statistics and regression modeling consistent with an introductory statistical course.
Module Content:
- Create and use RMarkdown
- Write, use, and debug custom functions
- Implement basic functional programming tools such as apply() to manipulate data
- Write and use control flow tools, including loops and if/else statments
- Understand and implement of object-oriented programming, including writing and using object-oriented code (e.g., S3/S4)
- Write and use R formulas, and explore their utility in common functions
- Implement bootstrapping to estimate confidence intervals
- Solve basic ordinary differential equations in R
- Optimize functions using the optim() function
Instructors
Isaac Fung, PhD
Isaac Fung, Associate Professor, Biostatistics, Epidemiology & Environmental Health Sciences
Dr. Isaac Chun-Hai Fung is an infectious disease epidemiologist with experience in mathematical modeling, data analysis, and digital health. He investigates the transmission of communicable diseases with a focus on respiratory infections and environmentally transmitted infections. He applied a variety of methods, from classical statistical methods to machine learning and mathematical modeling, to address public health problems and to provide solutions to policy-makers.
Zane Billings
Graduate Student
Zane Billings is a PhD student in Epidemiology and Biostatistics at the University of Georgia, working with Andreas Handel. He has been using R since 2017, and uses R for nearly all of his statistics and data science practice. Zane’s research focuses on the immune response to influenza vaccination, and uses machine learning and multilevel regression modeling (in R!) to improve our understanding of influenza immunology.
Required Software:
R + RStudio
