Associate Professor Sama Low-Choy
This interactive tutorial will redress a fundamental, subtle and often overlooked, topic in statistics: the logic of probability. Questions explored include: What is probability? What does it mean exactly? What are common misinterpretations and how can I avoid them? What is Bayes' theorem, and why is understanding it important to differentiating between different statistical approaches?
Understanding probability is an essential building block for anyone doing statistics in the 21st century, in an age when we need to be conversant in multiple statistical paradigms. These include: null hypothesis significance testing (in confirmatory analyses, or more broadly to ensure continuity with historical research), classical or Frequentist statistical modelling (e.g. involving maximum likelihood estimation, asympototic standard errors), machine learning algorithms (for analysis of big data, and often surprisingly have a statistical modelling analogue), Bayesian statistical modelling (for updating knowledge from non-informative or informative prior to posterior).
We will use role-play to help you really think through what probailities mean, and to become aware of common logical fallacies that can lead to unfortunate misinterpretations of probabilities, and hence lead to gross misconceptions about what statistical analysis provides.