Introduction to Power Analysis
Event box
Introduction to Power Analysis In-Person
Power analysis helps researchers determine whether a planned study has a reasonable chance of detecting an effect that matters. In this hands-on workshop, participants will learn the foundations of statistical power, calculate power and minimum detectable effects, and use R to examine how results change across assumptions about sample size, effect size, and outcome variability. We will also introduce Monte Carlo simulation for designs that simple formulas cannot adequately represent. Throughout the workshop, participants will connect power to the research question, planned statistical model, and study design.
Learning Objectives
By the end of the workshop, participants will be able to:
- Explain statistical power and its relationship to Type I and Type II errors.
- Calculate power and minimum detectable effects for a two-group comparison.
- Use R to examine power across a range of assumptions and identify a required sample size.
- Recognize when a standard formula is inadequate and use Monte Carlo simulation instead.
- Explain how the estimand, estimator, and study design jointly determine power.
Audience
Graduate students, faculty, and staff who are planning quantitative research or evaluating a study design. Familiarity with hypothesis testing and basic R syntax will be helpful, but prior experience with power analysis is not required.
Workshop Preparation
Participants should come prepared with R and Positron installed and working. The hands-on instruction will use R. A parallel Python deck and code will also be available.
Library workshop incentive attendance: Any student who attends at least three library workshops this semester will be eligible to receive a FREE Yale Library tote bag. Learn more.
- Date:
- Thursday, October 22, 2026
- Time:
- 10:00am - 12:15pm
- Time Zone:
- Eastern Time - US & Canada (change)
- Location:
- RKZ Library Classroom 01
- Campus:
- Science Hill
- Audience:
- Faculty Graduate Students Postdoc Staff Undergraduates
- Categories:
- Computational Methods and Data StatLab