CMSE 890-310: GAPS, MISSTEPS, AND ERRORS IN STATISTICAL DATA ANALYSIS
CMSE 890-310: GAPS, MISSTEPS, AND ERRORS IN STATISTICAL DATA ANALYSIS
November 9, 2020 - 3:00pmInstructor: Dr. Arjun Krishnan
This course is for students who want to understand common ways that statistics are done wrong. Topics include p-hacking, statistical power, pseudoreplication, and model abuse.
Register Now
Course runs: MW 3:00p - 4:50p. Due to the pandemic, Classes will meet via Zoom.
Classes will involve lectures, discussions, hands-on exercises, and homework about concepts critical to the day-to-day use and interpretation of statistical techniques.
Topics
Estimating error, uncertainty • Underpowered statistics • Multiple testing • P-hacking • Pseudoreplication • Regression to the mean • Double dipping • Spurious associations • Visualization challenges • Reproducibility, replicability • (Others under consideration; Subject to small changes)
Prerequisites
To get the most out of this course, it would be ideal if you have:
1) Familiarity with introductory statistics and probability, and
2) Basic experience with data wrangling, analysis, and visualization using R/Python.
- Prerequisite: CMSE890:302 or equivalent.
- Pointers to free online preparatory resources will be posted soon.
Students, postdocs, faculty welcome!
Instructor
Arjun Krishnan, Dept. Computational Mathematics, Science and Engineering, Dept. Biochemistry and Molecular Biology
arjun@msu.edu | https://thekrishnanlab.org | https://twitter.com/compbiologist | @Arjun Krishnan