Essential Data Analysis Skills for Biologists

Outline

This three day course is intended to open doors to applying statistics - whether directly increasing skills and personally undertaking analyses, or by expanding knowledge towards identifying collaborators. The end goal is to drive confident engagement with data analysis and further training - increasing the quality and reliability of interpretation, and putting that interpretation and subsequent presentation into the hands of the researcher. Each day of the course will deliver a mixture of lecture, workshop and hands-on practice.

Instructors

• Hugo Tavares
• Sandra Cortijo
• Aaron Lun
• Catalina Vallejos
• Aiora Zabala

Keynote lectures

• John Marioni
• Florian Markowetz

Aims

During this course you will learn about:

• The importance of Reproducible Research and how tools such as R can help
• Planning your experiment and why good experimental design is critical
• How to use spreadsheet programs (such as Excel) more effectively, and the limitations of such programs
• Writing and executing basic data analysis workflows in R
• Formulating and interpreting the result of a statistical test
• Choosing the appropriate graphics to understand and present your data

Objectives

After this course you should be able to:

• Identify sources of variation and confounding in your experimental design and prepare for a consultation with a statistician
• Assess the distribution of your data and choose the appropriate statistical test; recognising any limitations that may exist
• Create a reproducible piece of R code to import, visualise and perform a statistical test on biological data
• Know how to develop your data analysis skills after the course

Materials

Day One

• Experimental Design (lecture)
• Data Formatting and R introduction
• Reproducible Research (lecture)

Day Two

• Introduction to Statistical Thinking (lecture)
• Introduction to Rmarkdown and Statistics in R (practical)
• Introduction to Rmarkdown and Statistics in R (answers)
• Hypothesis Testing (lecture)
• Simple hypothesis testing in R (practical)
• Simple hypothesis testing in R (answers)

Day Three

• Regression analysis in R (lecture)
• Overview of linear modelling (practical)
• Overview of linear modelling (answers)
• Introduction to Scientific Figure Design (lecture)
• Introduction to Scientific Figure Design (practical)

Shiny apps

• The Central Limit Theorem
• Descriptive Statistics
• Standard Error versus Standard Deviation
• Data Exploration
• Linear Regression
• Simulating the p-value

Etherpad

Venue