Power and data simulation

This event is a short one-day workshop teaching data simulation in R. The aim is to give you hands-on experience simulating data, which in turn will help you develop a deeper understanding of key concepts in statistical analysis and experimental design. Specifically, the workshop aims to help you:

• Understand the basic idea of how data simulation works
• Understand why it is a good idea to simulate data for your own studies before you collect real data
• Simulate random data to help understand what p-hacking is and why it is a problem
• Simulate data with real effects to illustrate problems with low power in small sample sizes
• Learn how to simulate data for different research designs (e.g., repeated-measures)
• Familiarise with packages in R that are useful for data simulation

The workshop was designed by Prof Dorothy Bishop and will be delivered by Dr Jackie Thompson (U of Oxford).

It is free but places are limited and will be allocated on a first-come first-served basis.

Prerequisites: basic command of R.

• A very friendly and basic interface for learning R is here:https://swirlstats.com/

• There are various online courses on R from Data Carpentry and Software Carpentry that you can find by Googling: these are geared to different disciplines, and you may find it helpful to browse to find one most suited to your field. This one, although designated for Social Sciences, is a good introduction to the ‘tidyverse’ – a set of functions in R that make data manipulation relatively easy: https://datacarpentry.org/r-socialsci/. It also has a good first lesson to just help you find your way around R studio.
• A more in-depth online resource for learning R is Hadley Wickham’s book R for Data Science, available here: https://r4ds.had.co.nz/ . This is especially good for learning visualisation tools (how to make graphs, charts, etc.), and also has helpful introductory chapters on workflow basics in RStudio. It extensively covers the tidyverse.