Psychological Science & Statistics – From Inquiry to Insight
This mini-book is Track B in the PyStatsV1 documentation. It is written for undergraduate psychology students (and instructors) who want to connect:
core ideas from research methods and statistics,
with real, reproducible analyses in Python, and
with examples that look like actual psychology studies.
What this mini-book assumes
You have seen basic ideas like variables, hypotheses, and p-values.
You may have used SPSS, JASP, or jamovi before.
You are either new to Python, or you have only used it a little.
You do not need to be a math expert. We will emphasize:
research questions and study design,
good measurement and data collection,
clear, honest interpretation of results.
How this track is organized
The chapters are grouped into broad parts:
Foundations of psychological science: why we do experiments, threats to validity, and ethical research.
Describing and exploring data: distributions, visualization, and effect sizes that matter in psychology.
Comparing groups: one-sample, independent, and paired-samples t tests, plus power and planning.
Experiments and ANOVA: one-way and factorial designs, interactions, and planned contrasts.
Association and prediction: correlation, simple and multiple regression, and mediation-style thinking.
Advanced designs and capstone projects: mixed models, repeated measures, nonparametric tests, and full study write-ups.
PyStatsV1 labs
Most chapters include a PyStatsV1 lab:
a small, psychology-themed dataset (e.g., reaction times, mood ratings, memory scores, or intervention effects),
Python code that reproduces the main analyses,
and guidance on how to interpret the output as a researcher.
These labs live in the main PyStatsV1 repository so that you can:
run them locally in a notebook or Python script,
modify them for your own course or project,
and use them as templates for your own studies.
How to use this track
If you are a student:
Read the conceptual sections first.
Then open the matching PyStatsV1 lab and run the code yourself.
Try changing small pieces (sample size, effect size, model specification) and see how the results change.
If you are an instructor or TA:
Treat each chapter as a lecture + lab pairing.
Use the PyStatsV1 scripts as live demos or homework templates.
Mix and match chapters with your existing syllabus.
Where to go next
As we build out this track, new chapters will appear under:
on the left-hand sidebar.
For more detailed regression theory and diagnostics, you can also follow Track A – Applied Statistics with Python (Regression), which mirrors a classic applied regression course in a language-agnostic way (R ↔ Python).