MRes Experimental Psychology with Data Science

The topics covered will include:

• Using Conda to create reproducible Python environments  
• Programming in Python using Jupyter Notebooks  
• Data analysis using the NumPy, pandas (and related) Python libraries  
• How to use git and GitHub for version control and collaborative working  
• Making your analyses reproducible using Docker  
• Understand the principles of statistical/machine learning  
• Classification and resampling methods  
• Model selection and regularization  
• Unsupervised statistical learning

• To equip students with a range of advanced computational and analytical techniques.  
• To equip students with the confidence and skills necessary to apply the methods to datasets using Python  
• To provide sufficient understanding for sophisticated statistical decision-making and interpretation of results.  
• To contextualise statistical analysis in the context of the principles of reproducibility and Open Research.  

Having attended the unit, students will be able to:  

• conduct data analyses in Python  
• demonstrate their knowledge and skills required for open and reproducible science.  
• demonstrate their ability to understand the principles of statistical/machine learning.  
• demonstrate their ability to apply statistical learning methods on contextualised datasets.  

In Semester 2 there will be weekly 2-hour seminars providing an introduction and explanation of each technique and practical training. Each technique will be demonstrated using appropriate software.  

Continuous assessment. Two assignments. Each topic will be formally assessed by a written assignment, worth 50% of the marks for this module.

One assessment will be on programming and data analysis using Python  and the other assessment will be on applying statistical learning techniques to existing data

Appropriate online resources will be made available alongside each lecture.