Introduction

Stéphane Tuffier

2024-06-05

❔

… or about open access, open data, open methods/protocols, or open source?

How many of you have read a method in a paper and wondered how they actually did it?

Have you ever received confusing code? Or maybe written your own confusing code?

Reproducibility

Reproducibility

Obtain consistent results using the same data and code as the original study.

Replicability

Obtain consistent results across studies aimed at answering the same scientific question using new data or other new computational methods.

Unreplicability can be useful to science and help build knowledge.

• Domain of study
• Complex / unknown systems
• Researchers choices:
  • Study design
  • Mistakes
  • Misconduct
  • Poor reporting and publication bias

Source of not useful non-replication:

• publication bias
• misaligned incentives
• inappropriate statistical inference
• poor study design
• errors
• incomplete reporting of a study

Reproducibility

Related to data collection, computation, and analysis:

• Data acquisition
• Data management
• Analysis
• Reporting results

Important

Almost all the steps of an epidemiology study can be involved!

Reproducibility

Workshop organization

A little bit of theory and lots of hands-on exercises. Each part of the workshop has a dedicated page where you can find slides and instructions.

• Introduction (20 minutes): a little bit of theory

• Hands-on Activity 1: a simple reproducible project (40 minutes)

• Break (30 minutes)

• Hands-on Activity 2: create a nice report (50 minutes)

• Closing Remarks and Q&A (15 minutes)

Getting help

• Maybe your teammates can help

• Put a sticker on your computer if you need assistance

• Raise your hand

• No stupid questions—we’re all learning here, including me

  • Be open-minded

  • Be supportive

  • Be inclusive

Let’s form teams of 3

1. Have you ever created and used custom functions in R?
2. Do you ever have use map functions from purrr package?
3. Have you ever created a report using RMarkdown, Quarto or Jupyter notebook?

If you answered “No” to all three questions: Beginner

If you answered “Yes” to one or two questions: Intermediate

If you answered “Yes” to all three questions: Advanced

Let’s mix things up and get to know each other! We’ll form teams of 3 with varying levels of R experience.

References

National Academies of Sciences, Engineering, and Medicine. 2019. Reproducibility and Replicability in Science. Washington, DC: The National Academies Press. https://doi.org/10.17226/25303.

Peng, Roger D. 2011. “Reproducible Research in Computational Science.” Science 334 (6060): 1226–27. https://doi.org/10.1126/science.1213847.