PSYC 201B: Statistical Intuitions for Social Scientists

When and where?

Communication: Slack | Github
Location: Mandler 3545 (Crick Conference Room)
Lectures: Mon+Wed 2:00-3:50pm
Lab: Tues 5:00-6:50pm

About

As computers have become increasingly powerful modern statistical practice has changed, offering approaches that go far beyond standard methods taught in classic psychological statistics (Efron, Bradley, Hastie, Trevor 2016). And yet at the heart of these developments are just a handful of key ideas (Gelman, 2021). This course is designed to help you interactively develop your own statistical intuitions about these ideas using the Python programming language. At the core of the class is a deep understanding of the General-Linear-Model (GLM) from which we’ll build-up additional concepts (e.g. linear-contrasts, mixed-effects-models) and connect to related ideas in machine-learning (e.g. resampling, cross-validation, regularization).
Requirements: PSYC 201A or equivalent
Note: this course will be taught in the Python, but experience in another language (e.g. R, Matlab) is sufficient

Goals

• Build a strong foundation in statistics based on a deep understanding of the GLM

• Learn computational thinking, rather than statistical ritualizing - understanding the relationship between your analytic approach and what inferences are justified from first principles

• Develop practical Python programming, data analysis, and visualization skills

• Set you up for further coursework in advanced data-science, artificial intelligence, computational social science, or econometrics

Acknowledgments

This course draws inspiration from numerous sources including:

• Psych252: Statistical Methods by Tobias Gerstenberg

• Statistical Thinking for the 21st Century by Russ Poldrack

• DartBrains by Luke Chang

• Foundations of Data Science @ UC Berkley

Course logo for this year created with the assistance of GenAI

---

[EH16]

Bradley Efron and Trevor Hastie. Computer age statistical inference: Algorithms, evidence, and data science. Cambridge University Press, Cambridge, England, July 2016.

[GV21]

Andrew Gelman and Aki Vehtari. What are the most important statistical ideas of the past 50 years? Journal of the American Statistical Association, 116(536):2087–2097, October 2021.