Instructors: Jamie Moffa, MD/PhD student, and Tania Lintz, PhD student
This two-part series will introduce animal behavioral models you may come across when reading scientific papers, and the statistical principles used to analyze data. These sessions will include interactive lectures on behavioral models and the basics of statistics, demonstrations, and time for questions. No experience reading papers or analyzing data is necessary! NOTE: This agenda is flexible and will be adapted based on the needs and interests of the class and available resources.
Friday, June 23, 1-3 PM: An introduction to behavioral models and statistical analysis (Pt. 1)(CSRB NTA room 401, 4th floor)
We will first touch on the importance of behavioral research, then look at common examples of behaviors you might find when reading scientific papers. We will talk about how those experiments are set up, controlled for, made replicable, and how data presentation affects interpretation. We will go over the basic principles of data analysis, using data presented in part 1 of the session as a starting point. We will cover why statistical analysis is important, the basic principles behind common statistical tests, and common mistakes to look out for in your own and others’ work.
We will talk about:
- How animal models help us provide clinical answers
- Examples of common behavioral models
- What are comparable populations?
- What is a control and how do we make a good one?
- The importance of statistical analyses
- P values and how to compare control and experimental populations
- Variation, error & confidence intervals
Friday, June 30, 1-3 PM: Interactive dissection of behavior models and statistical analysis (Pt. 2) (CSRB NTA room 401, 4th floor)
We will build on last week’s lesson and discuss how to present behavioral data and spot common statistical errors, using real data. Students will then work in small groups to develop an experiment and plan appropriate analyses. Together, we will talk about:
- How to look at and present behavioral data
- “It’s a trap!” Common mistakes to watch out for
- Build-your-own behavior experiment