ReproNim Statistics Module

Here we describe some key statistical concepts, and how to use them to make your research more reproducible. This module is a part of the training curriculum from the ReproNim (Reproducible Neuroimaging) Center.

This course is a template for creating ReproNim training modules. The template for all ReproNim modules is based on the templates of Neurohackweek, Data Carpentry and Software Carpentry workshops.


09:00 An introduction to the Statistics in reproducibility module Who is this module for ?
How can I get some help if I get stuck on solving for an exercise or a question ?
How can I validate this module ?
09:00 Statistical basis for neuroimaging analyses: the basics Sampling, notion of estimation : estimates of mean and variances
Distributions, relation to frequency, PDF, CDF, SF, ISF
Hypothesis testing: the basics H0 versus H1
Confidence intervals
Notion of model comparison : BIC/Akaike
Notion of bayesian statistics
09:00 Effect size and variation of effect sizes in brain imaging Variance explained
What is an effect size, statistical versus biological or medical relevance
Why effect sizes vary: sampling, models, processing parameters, population, effect of unknown parameters
Other measures of effect size
14:00 P-values and their issues What is a p-value ?
What should I be aware of when I see a ‘significant’ p-value ?
14:00 About statistical power What is power
Why is it important: issues with low statistical power
Some tools for power for neuroimaging
17:00 The positive Predictive Value What is the positive Predictive Value (PPV) ?
17:30 Cultural and psychological issues What have we learned?
19:30 Finish