Course Introduction

Welcome and Introductions

Statistician that specializes in genetic data
Has used R (or S) since 1998, but didn’t really understand it until recently
- Was more of a C programmer
Disliked R for most of the last 16 years
Taught an R course two years ago
- When I finally learned R, I learned to love it
Seeing R incorporated into Reproducible Research excites me

In computational sciences and data analysis, let’s go with this definition:
- the data and code used to make a finding are available and they are presented in such a way that it is (relatively) straightforward for an independent researcher to recreate the finding.
This actually seldom happens. Consider two interesting articles by Tim Vines:
- The Availability of Research Data Declines Rapidly with Article Age “of 516 articles published between 2 and 22 years ago…the odds of a data set being extant fell by 17% per year.”
- Recommendations for utilizing and reporting population genetic analyses: the reproducibility of genetic clustering using the program structure “we reanalysed data sets gathered from papers using the software package ‘structure’… 30% of analyses were unable to reproduce the same number of population clusters.”
Scientific articles have fairly detailed methods sections, but those are typically insufficient to actually reproduce an analysis.
Scientists owe it to themselves and their community to have an explicit record of all the steps in an analysis done at a computer.

How do you efficiently record what it is you have done at your computer?
There would be lots of ways, but we will look at using 4 tools:
1. R – open source, free, industry-standard analysis software
2. RStudio – open source, free, environment for working with R
3. git – open source, free version control software (because research is never really linear when it is happening)
4. GitHub – website with tools making it very easy to collaborate with people using git.

Weekly format
- Tuesdays: R and RStudio
- Thursdays: How to write reports/articles using Rmarkdown. Using git and GitHub
However the course is integrated!
- Would be hard to just do Tu or just Th.
- We will use git to obtain and submit R homeworks, etc.
- This is how it works in real life too…

Note that you can see the raw rmarkdown source used to write each page.

Two years ago my course was focused on R as a programming language
Having satisfied my curiosity about that, this year I mostly want to teach people how to use R, practically, as a useful tool

Quick show of hands for NMFS Fed, NMFS Contractor, grad student, PCS, MBARI, others?
How about the range of experience with R and git?
Great that we have that much interest
But, it will dictate a few things about the course:
1. I won’t be able to answer everyone’s every question
  - “It takes a village”
2. My vision: we are a dedicated community of researchers that will work together, helping one another become fluent in these tools. So:
  - If a practical in-class exercise, or a homework assignment seems easy to you because you are already well-versed in R, then take a moment to help someone that is being challenged by it!
  - If you are new to all this, find someone in the class that can help you!
3. Please add comments to the DISQUS comment boxes on each page
  - Sign up with a reasonable identifier
  - Let’s crowd source solutions to issues that come up for people in the course!
  - Particularly for PC users (which I am not…)

Every page of this course is editable
If you see something that needs changing, you can do it and send me a pull request
This will make much more sense after a few more weeks.

There will be homework! (As long as I have time to write more…)
You can’t learn these methods without doing and using them
Amounts of HW should not be overwhelming.
I won’t be grading everything, but:
- I will establish “peer-review” system of homework
- Everyone will do homework and “referee” homework
- Doing this will let us get intimately familiar with how to use git and GitHub.
Familiar and advanced R users:
- Please contribute assignments and homework problems
- Once we have gotten the rudiments of GitHub down I will make a place for you to submit new homework problems