My academic research can be grouped into two broad categories. First, as a cognitive scientist, I am interested in how people acquire new knowledge and reason about the world; and as a mathematical psychologist my approach to studying this is to employ a mix of computational modelling and experimental work. The second broad topic I write about is methodological. What is the relationship between scientific and statistical inferences? How should researchers choose between competing theoretical models? I spend quite a lot of my time thinking about these questions. Some recent papers that I really like:
- Navarro, D. J. (2021). If mathematical psychology did not exist we might need to invent it: A comment on theory building in psychology. Perspectives on Psychological Science, 16(4), 707-716. [pdf, psyarxiv, osf, github, doi]
- Navarro, D. J. (2019). Between the devil and the deep blue sea: Tensions between scientific judgement and statistical model selection. Computational Brain and Behavior, 2, 28-34
- Navarro, D. J. and Kemp, C. (2017). None of the above: A Bayesian account of the detection of novel categories. Psychological Review, 124, 643-677
- Tauber, S., Navarro, D. J., Perfors A. and Steyvers, M. (2017). Bayesian models of cognition revisited: Setting optimality aside and letting data drive psychological theory. Psychological Review, 124, 410-441.
Texts and tutorials
One of my joys in life is writing tutorial articles and technical documentation for open source projects. In addition to writing the surprisingly successful learning statistics with R textbook, I’m currently collaborating with Hadley Wickham and Thomas Lin Pederson to write a third edition of the ggplot2 book. I am also weirdly passionate about creating accessible data science tutorials that I post on my youtube channel, and making my data science course materials open and freely available to the general public
I have several R packages at varying stages of development.
- Some packages are aimed for behavioural scientists: for instance, the jaysire package provides a method for writing behavioural experiments within R that can run through a web browser.
- Some packages are general purpose tools: the caladown package is designed to support lightweight blogs and websites designed with R users in mind and compatible with popular tools such as blogdown and hugodown. This website is an example of a calade themed site, and my art website is an example of a diziet themed site.
- Some packages exist as a small source of joy with a serious purpose in mind: the rainbowr package provides a way to generate LGBTIQ themed R hex stickers. It’s something that brings me joy but is also a small way to let other LGBTIQ people in the R community see themselves represented.
- Finally, there are a collection of packages I write to make it easier to create artwork in R: asciify, jasmines, scrawl, flametree, turmite59 and so on. These are mostly for my own joy, but again they serve a functional purpose: the scrawl and flametree packages are tools I’ve incorporated into my R classes, as a way for my students to learn programming concepts
R-Ladies is a worldwide organisation that promotes gender diversity within the R community. The organisation is explicitly LGBTIQ friendly and trans-inclusive, and aims to provide support in across the entire spectrum of roles whether as leaders, package developers, conference speakers, conference participants, educators, or users. In collaboration with Jen Richmond, Lisa Williams, Steph Stammel I helped to co-found the Sydney R-Ladies chapter in 2018, and it’s been one of the most rewarding professional activities I’ve ever been involved in.
Other community activities
I currently hold editorial positions at one of the top scientific journals (Science) and one of the top journals in psychology (Psychological Review). I previously served as an associate editor at three top journals in cognitive science and cognitive psychology: Cognitive Science, Behavior Research Methods, and Open Mind.