Paul Zivich
An essential part of quantitative sciences, like epidemiology, is computation. Often there are a variety of different options to compute a quantity. Having a good understanding of these essential methods provide a foundation to build complex quantitative analyses. Despite this importance, most curricula ignore these basic computational procedures.
This repository is a collection of tutorials focused on computational aspects of epidemiology to supplement what I see as a gap in most epidemiologic (and other quantitative sciences) curricula. Through simple examples, the basic principles of computational procedures common to epidemiologic analyses are reviewed. While the focus is on epidemiology (as I am an epidemiologist), the ideas and concepts explored here apply to any quantitative science.
While not part of an official course, this repo is made with the idea that it would become an epidemiology course in the future.
In the tutorials, I code in Python. This is for various reasons: (1) I work mostly in Python, (2) I have found Python to be quick readable, even to those who don't use it, (3) it is one of the most popular languages for quantitative sciences (even if epidemiology lags behind), (4) it is free to use, and (5) recoding what I have to a language you regularly use (e.g., SAS, R, Stata) will be more informative than simply running the code I provide.
I may try to provide code in other languages at some point.
To cover the basic computational tools for common epidemiology (and other quantitative science) tasks.
- Understand and implement different computational methods for basic quantities and be able to adapt these procedures
- Practice translation of mathematical formulas into code
- Develop best practices for coding
- L0: Basic data manipulation
- L1: Computing the proportion
- L2: Computing the variance
- L3: Computing the mean
- L4: Regression
- L5: Simulation
- L6: Differential equations
- L7: ?
- L8: Special topics
TBD