R Courses for Scientists
We are excited to offer three courses on R at UWA in June 2019. The first provides an introduction to R, the second focuses on creating publication-quality figures with R, and the third helps you extend your R skills to start to truly harness its power to deal with large data sets. See below for details about course content, and scroll to the bottom for details on course timing and location.
R is a free software environment for statistical computing and graphics. It is becoming more and more popular with biologists and ecologists as their statistical package of choice, due to the fact that it integrates data exploration, high-quality graphics and a huge range of statistical analysis. There is also a wide availability of on-line support forums, user groups, websites and books that guide the reader step-by-step through analyses, and the possibility of automating large analyses through scripting (not to mention the fact that it’s absolutely free!).
Each year I offer courses on R at UWA, and occasionally at other locations. The courses have a very practical focus, with a bare minimum of theory and lots of opportunity to practice with guidance. The courses also take a self-paced approach that lets participants absorb ideas and try out techniques at a speed that suits them. Example analyses mostly focus on ecological, agricultural or biological data sets. After mastering the basics, participants can focus on examples that are most relevant to their interest. Each course is usually 1.5 to 2 days long. The following are typical descriptions of available courses.
Introduction to R (or R refresher)
Heard about R, but didn’t know where to get started? Used R a little but struggling to get back into it, or harness it for more advanced methods? Course 1 provides an introduction to R suitable for people with little or no experience with R or any other particular software package, or for those wanting a quick refresher. We will cover the basics of the R interface; how to get data in and out of R; basic data exploration, including simple graphics; and statistical analyses such as t-tests, regression, ANOVAs, and ANCOVAs. We’ll also provide examples of more specialised analyses, such as generalised linear models, generalised additive models, and some multivariate analyses, for those who are interested. The course is designed to be flexible, so that complete beginners can focus on the basic examples, while those with some experience can move ahead quickly and try more advanced examples. This course may still be useful even if you did it before, if there were examples that you didn’t complete the first time.
Graphics with REverybody knows a good picture is worth a thousand words - and this is especially true in scientific reports and publications. A good graph will display your key research results in a clear and elegant way. But how do we make a good graph? Being able to make publication-quality graphics efficiently is an essential skill for researchers, and high quality graphics can even impress reviewers and give your publications that extra “edge” to make it in top journals. Many researchers create their graphs in Excel, which tends to be time consuming, limited in scope and flexibility, and often gives unsatisfactory results. Specialised graphical software packages exist, but these tend to be expensive and may still have limitations. This course will teach you how to make elegant, publication-quality graphics in the free, open-source R environment. We will cover examples that use the base R functionality, as well as examples that use the powerful ggplot2 add-on graphics package (also free). There will be time towards the end to try plotting your own data if desired.
Handling data with RHave you ever spent hours doing repetitive tasks manipulating data in Excel? Or days? Or weeks?!? And then realised that there was an error somewhere at the start and had to go back and do it all again? There is a better way! J This day will get you started with data manipulation and automation techniques that will save your time and possibly your sanity. You will learn how to extract subsets of your data, change the format of data, aggregate information across multiple factors, automate analyses across multiple datasets and files, automate manipulation of numerical and character data, and generally ‘do things with data’ in powerful and efficient ways. The techniques are especially powerful with big data sets, but will still prove useful even if your data sets are smaller. Some basics of R programming will be introduced, but we will mostly use relatively simple R functions.
Mixed effects modelling with R
This course is designed for anyone interested in understanding how, when and why to use mixed effects models to analyse scientific data. Mixed effects models are models that include both fixed and random effects. They are appropriate for a wide range of scientific data sets, and yet many people do not yet understand them or use them well. They can be used to analyse data sets where there is blocking, split-plots, nested or hierarchical structures, or repeated measures on the same individuals/plots/units (or all of the above!). This course will provide a clear introduction to mixed effects modelling in R, mainly focussing on ecological and biological examples. Topics covered include understanding and differentiating fixed and random effects; simple regression and ANOVA models with only fixed effects; recognising and analysing blocked experimental designs; recognising and analysing nested experimental designs; recognising and analysing split-plot designs experimental designs; putting it all together for more complex designs; unbalanced data sets with both explanatory covariates and factors; and generalised linear mixed effects modelling for analysing binomial or count data. The course is based around a series of examples, building from very simple to more complex (and realistic!).
We are excited to offer three of these courses at UWA in June 2019.
Which course(s) to do?
You can enrol in any or all of the courses. People with little or no experience with R should attend Course 1 (Introduction). It would help to have at least some R experience for Course 2 (Graphics), which could be obtained through doing the first course, but this is not absolutely necessary. Course 3 (Handling data) assumes some more experience with R, which can be obtained through doing Course 1. Courses 1 and 2 are likely to be of interest to a very wide range of people, while Course 3 is likely to be of most interest to those who handle larger amounts of data.
· Course 1 (Introduction to R) will be on Monday 17th June 900-1630 and Tuesday 18th June 900-1300.
· Course 2 (Graphics with R) will be on Thursday 20th June 900-1630 and Friday 21st June 900-1230.
· Course 3 (Handling data with R) will be on Monday 24th June 900-1630 and Tuesday 25th June 900-1300.
Venue: The venue will be the FNAS Central Undergrad Computer Lab (G.017) in the Agriculture North Building at UWA.
Cost: There is a discount for students (or other concessions), and also for people doing multiple courses. The price will be
· $380 for one course ($280 concession)
· $280 for each additional course ($200 concession)
Booking and payment options:
- You can register by sending your name, details of which course(s) you want to register for, your school name, relevant BU and the PG number to debit, to email@example.com with subject ‘UWA R courses’. Funds transfers will be made after the course.
- If this option is not possible for you, then please contact me for alternative arrangements.
There are a limited number of places available so reserve your place as soon as you can.
Detailed information will be provided to enrolled participants before the course starts, but if you have any queries now, please contact Michael: firstname.lastname@example.org