Methods of Research
in Psychology I
Graduate training in applied data analysis for behavioral scientists — rigorous methods, human-centered questions, real-world impact.
Course Overview
The course has twelve modules across three parts. M01 is a self-study refresher to do before the semester starts; M02–M12 are covered during class, one per week, with each module-week following the Friday → Monday → Wednesday rhythm described below.
Foundations of Data Analysis in R
M01 refreshes the introductory-stats concepts you need before Week 1; M02–M05 then build the R toolkit — RStudio, Quarto, ggplot2, dplyr/tidyr, and descriptive-statistics workflows — that the rest of the course rests on.
Statistical Inference
How to reason rigorously under uncertainty: probability, confidence intervals, the logic of null hypothesis testing, and how to conduct and report significance tests in practice.
Model Building
Regression as the workhorse of applied behavioral research: simple and multiple linear models, partial-effect interpretation, the estimand-centered workflow, and the assumption-checking toolkit.
The Weekly Pattern
Most weeks follow the same three-session rhythm. Read the module on your own first, then the Friday pre-study builds on it — so you come to Monday ready to go deeper.
After reading the module on your own, watch the brief recorded videos and complete the warm-up activities — 10:00–11:00 am online, or any time before Monday's lecture.
We meet to apply the material, press further, and work through harder problems together — 10:00–11:30 am.
Hands-on coding in RStudio and R — practice what you learned this week in a structured lab exercise — 3:30–4:45 pm.
First week (Aug 24) is the exception — no Friday pre-study. We meet for the first time at Monday’s orientation lecture (M02 · Introduction to Tools), then set up your project workflow together in Wednesday’s lab. The full Friday → Monday → Wednesday rhythm begins in Week 2.
Part 1 · Foundations of Data Analysis in R
M01 is a self-study refresher of the introductory statistics you need to be successful in PSY 652 — read it before Week 1 to identify any rust to brush off. M02–M05 then build the R toolkit you’ll lean on for the rest of the course: R + RStudio + Quarto + version control (M02), the grammar of graphics (M03), data wrangling with the tidyverse (M04), and descriptive-statistics workflows with skimr / gtsummary (M05).
Part 2 · Statistical Inference
Statistics is a way of reasoning under uncertainty — not a recipe book. These four modules build the conceptual foundation you need to interpret results critically, avoid common inferential errors, and communicate uncertainty honestly.
Part 3 · Model Building
Regression is the engine of applied behavioral research. These three modules take you from a simple linear model through multiple predictors and partial-effect interpretation to the diagnostic toolkit for everything OLS rests on — and the remediation moves when an assumption doesn’t quite hold. Moderation, non-linear-in-predictors, causal inference with DAGs, and the GLM family are taken up in PSY 653.
marginaleffects, and the Table 2 fallacyWeekly Schedule
Each module week follows the Friday → Monday → Wednesday pattern described above.