UQ’s 2027 Summer R Workshops Cover R, Statistical Modelling and Spatial Analysis

The Centre for Biodiversity and Conservation Science’s 2027 Summer R Workshops at the University of Queensland are built around a practical need: researchers must be able to judge whether an analysis is sound, even when AI tools can produce code quickly. The February program moves from R fundamentals to spatial modelling, giving participants a path from data handling to more advanced methods. That progression reflects a basic reality of research computing: producing code is only one step, and a plausible result can still rest on an unsuitable method or a mistake in the data.

Five days, five topics

Each workshop stands alone, so participants can choose the sessions that match their experience and research needs. The schedule runs from Monday 8 February to Friday 12 February 2027:

• Monday 8 February: Introduction to R and data wrangling with the tidyverse
• Tuesday 9 February: Data visualisation and linear modelling
• Wednesday 10 February: Generalised linear modelling
• Thursday 11 February: Mixed modelling
• Friday 12 February: Spatial modelling, including temporal and spatial autocorrelation

The sequence offers a useful map of common analytical work. Data wrangling and visualisation help researchers understand what they have before they fit a model; the later sessions turn to methods for questions involving different kinds of outcomes, grouped data, or patterns across time and space. A one day format can introduce these ideas, though applying them well still depends on the research question, the quality of the data and practice after the course.

Because the sessions stand alone, attendees aren't required to take the whole week to benefit. That flexibility may suit researchers who already use R and want to concentrate on a particular method, as well as those who need an introduction before tackling modelling. The tradeoff is that participants will need to choose carefully: the schedule gives a topic list, but the available information doesn't specify prerequisites or how much material each session covers.

The sessions are hands-on, with code and learning materials provided. Most examples use ecological data, but the analytical approaches can also apply to other research fields. Working through code matters because statistical concepts become easier to assess when participants can see how data, model choices and outputs relate. The workshops are held in person; there’s no online option.

Why R fundamentals still matter

AI can draft code, but researchers still need to assess whether a method fits the question, whether its assumptions hold and whether the conclusions are defensible. A working grasp of R helps participants inspect generated code, catch errors and stay responsible for the analysis. This is more significant than it looks: a program can run without producing an answer that meaningfully addresses the research question.

Here's the thing: code is not a substitute for statistical judgment. A researcher needs to know what the analysis is intended to estimate, what conditions its interpretation depends on, and whether the data support those conditions. AI may speed up routine coding, but it can't remove the need to make and explain those decisions. An error can also be subtle: the output may look orderly while a variable, assumption or modelling choice has been handled poorly.

That judgment is especially relevant across the week's topics. Visualisation can reveal patterns that deserve closer examination, while modelling provides ways to describe relationships under stated assumptions. Mixed and spatial models address structures that simpler approaches may not capture. And this is the part most people overlook: knowing how to run a method doesn't by itself establish that it's the right method for a particular study.

If you're working in this space, the practical aim is to become a more informed user of analytical tools, whether code is written by hand or drafted with AI assistance. The workshop format may help participants connect the mechanics of R with the reasoning behind an analysis. A useful foundation, then—not a guarantee that every model choice will be straightforward.

What the program offers researchers

The week’s range gives researchers a way to target a specific gap or build skills in sequence, from handling data to modelling more complex patterns. Its ecological examples anchor the teaching in a clear research context, while the methods may be relevant beyond ecology. That combination is potentially useful for people who want practical instruction without treating one field’s examples as the limit of the techniques.

Registration for the February workshops is open. Details on course topics and participant testimonials are available on the workshops website. Questions about registration can be sent to cbcs-workshops@uq.edu.au.

The program is presented by the Centre for Biodiversity and Conservation Science. Its practical value is the range: participants can build core data skills or focus on modelling methods that support more demanding research questions. For prospective attendees, the key decision is which parts of that range match their current work—and whether they can attend in person during the scheduled week.