Work session: Exercise 05 and Final Project proposals

2024-10-04 Fri

Rick Gilmore

Prelude

Plot your data!

Matejka & Fitzmaurice (2017)

Overview

Announcements

• Due
  • Exercise 04: Violations of scientific integrity

On p-values

P-values can indicate how incompatible the data are with a specified statistical model. (Wasserstein & Lazar, 2016)

• (Improved) vocabulary
• We have to pick a statistical model (e.g., normal distribution or t distribution, or…) for our comparison
• What if our data don’t fit the model?

Last time…

• Do you sympathize with Stapel? Why or why not?
• Have you been in situations like Stapel describes where you have been asked to make a messy and complicated problem simpler?
• Do you think that academic science is becoming a business? Why or why not?
• Why is “massaging of data” or selective reporting of experiments a problem?
• Were the punishments in these cases fair and just or unfair and unjust? Why or why not?

Today

Work session: P-hacking & Final project proposals

• Assignment
  • Exercise 05: P-hack your way to scientific glory write-up.
• Work session
  • Final project proposals, due Friday, October 13.

Next time

Retraction and scientific integrity

On Zoom: https://psu.zoom.us/my/rogilmore. Check-in for attendance. Join from anywhere convenient to you.

• Read
  • Brainerd & You (2018)

Resources

References

Brainerd, J., & You, J. (2018). What a massive database of retracted papers reveals about science publishing’s “death penalty.” Science. https://doi.org/10.1126/science.aav8384

Matejka, J., & Fitzmaurice, G. (2017). Same stats, different graphs: Generating datasets with varied appearance and identical statistics through simulated annealing. In Proceedings of the 2017 CHI conference on human factors in computing systems (pp. 1290–1294). New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3025453.3025912

Wasserstein, R. L., & Lazar, N. A. (2016). The ASA’s statement on p-values: Context, process, and purpose. The American Statistician, 70(2), 129–133. https://doi.org/10.1080/00031305.2016.1154108