Data Analysis in R

Overview

Data Analysis in R helps you analyse data but also to understand and critically evaluate scientific literature, design your own experiments and report your results.

Learning Data Analysis is important…

The scale and complexity of biological data, and the need for responsible stewardship mean that all biologists are expected have the skills needed to design reproducible workflows for simulating, collecting, analysing and presenting data. Coding is at the heart of reproducibility because it explicitly describes everything you do with your raw data making your work completely transparent and reproducible.

The good news is that generative AI tools like ChatGPT and GitHub Copilot have transformed what is possible for non-programmers. Writing code is no longer the barrier it once was - if you can describe what you need you can get working code back in seconds. But working code is not enough - code can run and not be doing what you think it is. That ability to precisely describe what you want and knowing how to question and validate what AI produces comes from learning to code.

Research consistently shows that AI coding assistants work best for people who already understand the code being generated. Without that foundation, it’s hard to know when the output is wrong, incomplete, or quietly doing something other than what you intended. A little coding knowledge helps you write better prompts and know when to trust the result.

… and takes time …

Part of the reason that these skills are in-demand is that they take time and practice to learn just as playing an instrument, speaking another language or playing a sport take time and practice. They are skills you develop more than facts you memorise. You will make a lot of mistakes.

… but can be great fun …

There is a lot of problem solving which is engaging work because there’s always something to ‘chase’. You may be able to concentrate on coding for much longer than on writing or reading because it is such an active learning process. You’ll create impressive looking figures, which you can reproduce on a different dataset in moments, reveal exciting biological insights through data visualisation and analysis and learn whole world of ‘techy’ tricks you had no idea you’d be able to do!

The time and effort you put in to learning “Data Analysis in R” will reward you no matter how you evaluate yourself. You will be able to:

better and/or more quickly design and analyse scientific investigations for modules and projects in which in turn will allow you to perform better in assessments.
evaluate and interpret the data analysis in papers
access a wide range of careers

… and there’s help!

There is a book to support the Data Analysis in R content in your degree: Computational Analysis for Bioscientists

What is this site for?

All the Data Analysis in R teaching is on the VLE so why is this site useful? Well, perhaps more than any other material, you will want to refer back when applying your skills throughout your degree. This site collects everything together and is searchable. The search icon is on the top right.

Make a suggestion

Those with GitHub accounts can make a suggestion directly from the webpage. When you find errors – from simple typos to more troublesome issues – or want to make a suggestion, please use the “Make a suggestion” link on the right. This will open an “issue” on github (where the site is hosted) where you can let me know about the error or suggestion.

There is absolutely no requirement to use Git or GitHub in the BABS modules.

--- title: "Data Analysis in R" toc: true toc-location: right --- # Overview Data Analysis in R helps you analyse data but also to understand and critically evaluate scientific literature, design your own experiments and report your results. ## Learning Data Analysis is important... The scale and complexity of biological data, and the need for responsible stewardship mean that all biologists are expected have the skills needed to design reproducible workflows for simulating, collecting, analysing and presenting data. Coding is at the heart of reproducibility because it explicitly describes everything you do with your raw data making your work completely transparent and reproducible. The good news is that generative AI tools like ChatGPT and GitHub Copilot have transformed what is possible for non-programmers. Writing code is no longer the barrier it once was - if you can describe what you need you can get working code back in seconds. But working code is not enough - code can run and not be doing what you think it is. That ability to precisely describe what you want and knowing how to question and validate what AI produces comes from learning to code. Research consistently shows that AI coding assistants work best for people who already understand the code being generated. Without that foundation, it’s hard to know when the output is wrong, incomplete, or quietly doing something other than what you intended. A little coding knowledge helps you write better prompts and know when to trust the result. ## ... and takes time ... Part of the reason that these skills are in-demand is that they take time and practice to learn just as playing an instrument, speaking another language or playing a sport take time and practice. They are skills you develop more than facts you memorise. You will make a lot of mistakes. ## ... but can be great fun ... There is a lot of problem solving which is engaging work because there's always something to 'chase'. You may be able to concentrate on coding for much longer than on writing or reading because it is such an active learning process. You'll create impressive looking figures, which you can reproduce on a different dataset in moments, reveal exciting biological insights through data visualisation and analysis and learn whole world of 'techy' tricks you had no idea you'd be able to do! The time and effort you put in to learning "Data Analysis in R" **will** reward you no matter how you evaluate yourself. You will be able to: - better and/or more quickly design and analyse scientific investigations for modules and projects in which in turn will allow you to perform better in assessments. - evaluate and interpret the data analysis in papers - access a wide range of careers ## ... and there's help! There is a book to support the Data Analysis in R content in your degree: [Computational Analysis for Bioscientists](https://3mmarand.github.io/comp4biosci/) ## What is this site for? All the Data Analysis in R teaching is on the VLE so why is this site useful? Well, perhaps more than any other material, you will want to refer back when applying your skills throughout your degree. This site collects everything together and is searchable. The search icon is on the top right. ## Make a suggestion Those with [GitHub](https://docs.github.com/en/get-started/start-your-journey/about-github-and-git#where-do-i-start) accounts can make a suggestion directly from the webpage. When you find errors – from simple typos to more troublesome issues – or want to make a suggestion, please use the "Make a suggestion" link on the right. This will open an "issue" on github (where the site is hosted) where you can let me know about the error or suggestion. **There is absolutely no requirement to use Git or GitHub in the BABS modules**.