Rigor and Reproducibility in Experimental Design

This lesson introduces the foundations of sound experimental design and the importance of rigor and reproducibility in experimentation. The goal of this lesson is to provide conceptual understanding, methods, and practice in planning and evaluating experiments. Lesson structure is informed by Teaching Experimental Design by Derek J. Fry.


Learners need to be able to:


Setup Download files required for the lesson
00:00 1. Introduction What is reproducibility?
What is replicability?
Why are replicability and reproducibility important?
00:15 2. Why we need better design Why does good experimental design matter?
What are some of the consequences of poor experimental design?
00:45 3. Common failings What are some common features of poor experimental design?
What are some consequences of poor experimental design?
01:20 4. Types of experiments What are the features of different kinds of experiments?
What are my experimental units?
01:20 5. Experimental designs What are my experimental units?
How will treatments be assigned?
What are some types of experimental design?
01:20 6. Planning an experiment ?
01:20 7. Power calculation and sample size What role does the p-value (alpha) have in determining sample size for a study?
What is type 2 error, and how does it correspond to the p-value and power of a test?
What factors should be considered when estimating sample size for a study?
01:20 8. Linear regression and analysis of variance How do I evaluate the quality of a linear model?
What are the components that make up a one fixed factor linear regression model?
What are the assumptions of linear regression, and how can you test for them?
What are residuals and why are they important?
When should outliers be removed from a study?
01:20 Finish

The actual schedule may vary slightly depending on the topics and exercises chosen by the instructor.

This lesson was funded by NIH grant R25GM123516 awarded to Dr. Gary Churchill at The Jackson Laboratory.