class: center, middle, inverse, title-slide # Rethinking teaching statistical computing ### Nicholas Tierney <br> <br> Monash University ### SSA Vic Meetup <br> <br> Tuesday 31st July, 2018 <br> <br> .hugew[njtierney.com/talks] --- class: middle, inverse, center # Who has taught Statistics? --- class: center, inverse, middle # Who is _being_ taught statistics? --- class: center, inverse, middle # Meet your neighbour .large[ > "What are you teaching?" > "What are you learning?" > "Who taught you statistics?" ] --- class: center, inverse, middle # Who thought they had to learn programming? --- class: center # Pi-shaped researcher <img src="https://imgs.njtierney.com/pi-vs-t-research.png" width="100%" /> .pull-left[ [Image from Jake van der Plas](https://jakevdp.github.io/blog/2014/08/22/hacking-academia/) ] ??? [Ville Tervo](https://futurice.com/blog/from-t-to-pi-design-skill-expectations-in-change) [Jake van der Plas](https://jakevdp.github.io/blog/2014/08/22/hacking-academia/) In the words of Alex Szalay, these sorts of researchers must be "Pi-shaped" as opposed to the more traditional "T-shaped" researcher. In Szalay's view, a classic PhD program generates T-shaped researchers: scientists with wide-but-shallow general knowledge, but deep skill and expertise in one particular area. The new breed of scientific researchers, the data scientists, must be Pi-shaped: that is, they maintain the same wide breadth, but push deeper both in their own subject area and in the statistical or computational methods that help drive modern research: --- background-image: url(https://gifs.njtierney.com//moar-pi-small.gif) background-size: contain background-position: 50% 50% class: center, bottom, inverse --- class: inverse, middle, center # My journey --- class: center, inverse # Psychology <!-- --> --- class: center, inverse # PhD statistics <!-- --> --- class: inverse, center # Teaching statistics <img src="https://imgs.njtierney.com/broom-headshot-small.jpg" width="50%" /> --- class: inverse, middle, center # R packages <img src="https://imgs.njtierney.com/hex-visdat-and-naniar.png" width="80%" /> .pull-left[ .center[ .hugew[ visdat.njtierney.com ] ] ] .pull-right[ .center[ .hugew[ naniar.njtierney.com ] ] ] --- class: center # Post Doc .pull-left[ <!-- --><!-- --> ] .pull-right[ <!-- --><!-- --> ] --- background-image: url(https://imgs.njtierney.com/carpentries.png) background-size: contain background-position: 50% 50% class: center, bottom, inverse --- background-image: url(https://imgs.njtierney.com/how-learning-works-cover-small.png) background-size: contain background-position: 50% 50% class: center, bottom, inverse ??? s - discuss how I took this course --- .vlargeb[ **Learning** is a three part process, in which a student: 1. **Receives** information accurately 2. **Remembers** the information (long term memory) 3. In such a way that they can **reapply** the information when appropriate (**Teaching** is whatever helps a student do that) ] [Taken from Garret Grolemund's Teach the Tidyverse](https://github.com/rstudio-education/teach-the-tidyverse/blob/master/01-Two-Ways-to-Teach.pdf) --- background-image: url(https://imgs.njtierney.com/tower-of-babel.gif) background-size: contain background-position: 50% 50% class: center, bottom, inverse --- # Course climate: .vlargeb[ - Establish early - Make Uncertainty Safe - Get students talking < 5 min - Resist a Single Right Answer ] --- # Course climate: .vlargeb[ Watch dismissive language > "This has an **obvious** solution" > "**Just** download the R package" > "Oh that's **easy**, **just** do this ..." > "**Simply**..." ] --- # Feedback .vlargeb[ Frequent Feedback Opportunities ] [Meghan Duffy's: "Sticky Notes as a teaching and lab meeting tool"](https://dynamicecology.wordpress.com/2015/01/13/sticky-notes-as-a-teaching-and-lab-meeting-tool/) .pull-left[ <!-- --> ] .pull-right[ <!-- --> ] --- # Understanding learning .vlargeb[ - Growth and fixed mindsets - Reframe success + failure as opportunities for growth ] --- .center[ # Reframing ] .pull-left[ # From .large[ > "I'll never understand" > "I just don't get programming" > "I'm not a maths person" ] ] -- .pull-right[ # To .large[ > "I understand more than I did this morning" > "I can learn how to program" > "Compared to this morning, I've learnt quite a bit!" ] ] --- # Practical approaches .vlargeb[ - Balance Lecture with Exercise: - 5-10 min lecture, then - 1-10 min exercises - Use live coding ] ??? - Early Success Opportunities - Teach vis first ---3 class: inverse, center, middle # Live coding? > with rmarkdown! ??? --- # Recap .vlargeb[ - Course climate: Establish early - Provide Frequent Feedback Opportunities (sticky notes) - Understand growth and fixed mindsets - Balance Lecture with exercise - Use live coding - Teach using R Markdown ] --- # Where to from here? .large[ - [How learning works](https://www.amazon.com.au/How-Learning-Works-Research-Based-Principles-ebook/dp/B003IEJZXS) - [RStudio education](http://github.com/rstudio-education) - [The carpentries: instructor training](https://carpentries.github.io/instructor-training/) - [The carpentries - how we operate](https://carpentries.github.io/instructor-training/20-carpentries/index.html) - [The carpentries - live coding](https://carpentries.github.io/instructor-training/15-live/index.html) - [Garrett Grolemund's advice on teaching](https://community.rstudio.com/t/looking-for-best-ways-in-teaching-r-to-absolute-beginners/6998/3?u=apreshill) - [Learning rmarkdown](https://rmarkdown.rstudio.com/lesson-1.html) - [Meghan Duffy's: "Sticky Notes as a teaching and lab meeting tool"](https://dynamicecology.wordpress.com/2015/01/13/sticky-notes-as-a-teaching-and-lab-meeting-tool/) - [Garret Grolemunds Teach the Tidyverse](https://github.com/rstudio-education/teach-the-tidyverse/blob/master/01-Two-Ways-to-Teach.pdf) - [Article by Jake van der Plas on the pi-shaped research](https://jakevdp.github.io/blog/2014/08/22/hacking-academia/) - [Ville Tervo article on T and Pi skills](https://futurice.com/blog/from-t-to-pi-design-skill-expectations-in-change) ]