Publications by Bluecology blog
Stay motivated with R programming by knowing your emotions
Stay motivated with R programming by knowing your emotions We don’t usually think of programming as an ‘emotional’ experience. It is all code and computer logic and if using R, probably statistics. But recognising the emotions you face when programming can help you be more productive. In fact if you ask R about emotions it will probably tel...
1207 sym
Checking residual distributions for non-normal GLMs
Checking residual distributions for non-normal GLMs Quantile-quantile plots If you are fitting a linear regression with Gaussian (normally distributed) errors, then one of the standard checks is to make sure the residuals are approximately normally distributed. It is a good idea to do these checks for non-normal GLMs too, to make sure your residu...
5363 sym R (2089 sym/12 pcs) 10 img
General Linear Models The Basics
General Linear Models: The Basics General linear models are one of the most widely used statistical tool in the biological sciences. This may be because they are so flexible and they can address many different problems, that they provide useful outputs about statistical significance AND effect sizes, or just that they are easy to run in many comm...
8479 sym R (931 sym/10 pcs) 10 img
How do I calculate the R squared metric for a Bayesian model
How do I calculate the R squared metric for a Bayesian model? A good friend I met on a field trip long ago, Dominique Roche, recently emailed me to ask about evaluation of Bayesian models. He has been delving into generalized linear models, using Bayesian methods, and needed to decide what criteria he should use for model simplification (the proc...
6246 sym
Should I learn sf or sp for spatial R programming
Should I learn sf or sp for spatial R programming? I recently received an email about some of the short-courses on my webpage. The correspondant was asked whether my course on Maps and GIS in R was still relevant, it being written in 2014. The R environment is changing so fast, it is worth asking whether course material that is a few years old is...
4531 sym
How do I interpret the AIC
How do I interpret the AIC? My student asked today how to interpret the AIC (Akaike’s Information Criteria) statistic for model selection. We ended up bashing out some R code to demonstrate how to calculate the AIC for a simple GLM (general linear model). I always think if you can understand the derivation of a statistic, it is much easier to r...
8596 sym R (1988 sym/13 pcs) 8 img
A brief guide to data visuals in R in 2018
Data visuals 2018 Supplementary notes for CJ Brown’s talks on dataviz in 2018 for Griffith University’s honours students and the UQ Winterschool in Bioinformatics. These notes run through some of the principles I present and also show R code for generating data visuals. If you want to take the dataviz quiz first, then click here. We will look...
11159 sym R (10131 sym/40 pcs) 66 img
Survey your audience and visualise the results with R and Google forms
Survey your audience and visualise the results with R and Google forms I wanted to make my presentation on dataviz at the UQ School of Bioinformatics more interactive. A quiz is a good way to engage your audience. Given I was giving a talk about R datavisuals I thought it would be fun to visualise the quiz results using R live with the audience. ...
3951 sym R (913 sym/7 pcs) 2 img
Beginner Intermediate and Advanced R courses February 2019
Beginner, Intermediate and Advanced R courses February 2019 This is an announcement of our next set of R courses. There are 4 separate courses taught over 5th-8th February 2019. You can register with the Centre for Applications in Resource Management site at the University of Queensland. These R workshops are especially tailored for biology/ecolo...
2872 sym
Generalized Linear Models understanding the link function
Generalized Linear Models: understanding the link function Generalized Linear Models (‘GLMs’) are one of the most useful modern statistical tools, because they can be applied to many different types of data. Count, binary ‘yes/no’, and waiting time data are just some of the types of data that can be handled with GLMs. We often call such d...
14097 sym R (1972 sym/9 pcs) 14 img