Week 6 - Monday, April 20th

Announcements and Agenda

Today’s Objectives :

Practice with Interaction Effects and Power. Still good to review!
Discussing the Research on Dehumanization. Replication and need for transparent science.
The Learning Has Not Stopped. On extensions of the linear model (GLM –> HLM).

Agenda

10:10 - 11:00. Check-In (Interaction Effect and Power)
11:00 - 11:30. ACTIVITY : Experiments are Models.
11:30 - 11:40. BREAK TIME
11:40 - 1:00. More Linear Models

Class Slides and Material

Check-In : practice interpreting linear models and NHST.
Anchoring Data : for the in-class activity
Professor Notes. My R scripts and other notes, saved in real-time.
VISION BOARD. Where we will share work we do in class.

Additional Reading and Support Materials

Optional Readings on Cross Validation

Optional Readings on Errors in Our Predictions of People.

ARTICLE : Meyer, G. J., Finn, S. E., Eyde, L. D., Kay, G. G., Moreland, K. L., Dies, R. R., Eisman, E.J., Kubiszyn, & Reed, G. M. (2001). Psychological testing and psychological assessment: A review of evidence and issues. American psychologist, 56(2), 128.
Funder DC, Ozer DJ. Evaluating Effect Size in Psychological Research: Sense and Nonsense. Advances in Methods and Practices in Psychological Science. 2019;2(2):156-168. doi:10.1177/2515245919847202
Allen C, Mehler DMA (2019) Correction: Open science challenges, benefits and tips in early career and beyond. PLOS Biology 17(12): e3000587. https://doi.org/10.1371/journal.pbio.3000587

For Next Week.

Lab 6. Teaching Problems

The goal of this final lab assignment is to write a tutorial that walks a hypothetical student through interpreting the results of regression.

What this lab looks like is open-ended, but it should be (a) engaging (e.g., is written with the goal of teaching someone in mind) and (b) transparent (e.g., includes the dataset so a student can follow along).

More specifically, your tutorial should include the following.

Definig the problem and dataset. A clearly stated research question and theory you can test with the variables in the dataset.
Data cleaning and descrption. Explain how to graph the variables needed to for your model, and doing any data cleaning or transformations needed.
The basics of regression. Defining the needed linear model(s) to test your theory, and interpreting the slope(s), intercept, and \(R^2\) for your model. Include a graph for at least one model, and connect the statistics to your graph. Then, diagnose those assumptions of regression.
The basics of inferential statistics. estimate and interpreting sampling error of the linear models (using either bootstrapping or NHST.)
Interaction Effects. Define, testing, and interpreting an interaction effect (along with a graph!) and interpreting the slope(s) and \(R^2\) value from this model.
Choose one of the following : something more advanced (or new)!
1. Explain how a linear model changes after some transformation (e.g., z-scoring, log the DV, adding a quadratic term to the model.)
2. Teach us some new method, and explain why this is helpful or important in terms of your research question!

Feel free to keep this as short and streamlined as possible, but the idea is that someone could read through this and learn a little bit about the theory and practice of linear regression.

When you are done, please submit this tutorial to the bCourses assignment, and then upload a link to the dataset and your tutorial as a .PDF to the Vision Board.

Article Discussion

Scan the article below; we will briefly discuss next week!

Makin, T. R., & Orban de Xivry, J. J. (2019). Ten common statistical mistakes to watch out for when writing or reviewing a manuscript. Elife, 8, e48175. [PDF]
Submit Your Response Here. We’ll use these responses to guide our discussion of the article next week. Great to use your own voice; don’t worry about sounding smart or having “perfect” english!