Publications by Analysis of AFL
Data Viz The Glossy
One of the fun things when doing graphs, is that moment when you identify something that sticks out. A great example of this is done by ethan_meldrum In it we can see how much Paul Seedsman 2018 has stood out so far. Lets give it the ggplot/fitzRoy treatment. Step One – Get the Data library(fitzRoy) library(tidyverse) df<-fitzRoy::player_stat...
3388 sym R (2620 sym/4 pcs) 2 img
Plotting Background Data
One of the best things about the online R community is there are lots and lots of great people to follow online especially. One person I follow dataandme consistently links great how to do things on R tutorials. Recently I saw this post where she linked a post by drsimonj running through how to plot background data in R. My first thought as when ...
5681 sym R (8735 sym/14 pcs) 16 img
Is There Another Way to Do Fantasy
Apologies for the rushed nature of post Recently I saw this post on twitter and it got me thinking is there another way? So lets run through the rough problems as outlined in this tweet. Numbers have context (suprising I know!) What time period is best when looking at fantasy score history The general gist of the post is that Max Gawns numbers ...
2282 sym R (5331 sym/6 pcs) 6 img
Max Gawn a Brownlow Fancy
This week in AFL Nathan Fyfe one of the brownlow favourites got rubbed out for an ear tickler to Levi Greenwood When looking at the Brownlow odds, its a bit surprising to see Max Gawn listed as the second favourite. While he is having a great season, historically Ruckman have not polled well. But is Max having a Brownlow worthy year? Max Gawn Br...
6517 sym R (6669 sym/14 pcs) 16 img
Linear Regression an Introduction Through AFL
Linear regression is an amazingly powerful concept in statistical modelling. It forms a major part of lots of first year statistics cources and how to deal with problems with linear regression can form second year units by themselves! This post goal is to through the use of AFL data provide an intituitive guide to linear regression. So why use AF...
8195 sym R (4817 sym/5 pcs) 2 img
Regression to the Mean
We also see this in sports, Hollinger refers to it as the fluke rule. Bill James calls it the plexiglas principle, you might call it the Sports Illustrated Jinx. They all are different names from different people who have observed the same thing mean reversion or regression to the mean. Regression to the mean as a concept was first introduced in ...
4471 sym R (5168 sym/10 pcs) 6 img
Score Involvements
Got an email from someone who was reading the footballistics book they were really into it and got up to chapter 3. They must be a really big Western Bulldogs fan who has a lot of theories as to why after their premiership year in 2016 it seems they have dropped off suddenly, perhaps it has something to do with their spread of score involvements ...
1981 sym R (3973 sym/5 pcs)
The Fundamental Principles of Analytical Design
I have just finished reading the book Beautiful Evidence by Edward Tufte and in it he talks about the fundamental principles of analytical design. Henri Matisse I do not paint things, I paint only the differences between things Show Comparisons, Contrasts, Differences When looking at a graph or reading a statistic a good question and perhaps e...
3653 sym R (2048 sym/6 pcs) 12 img
Bradley Terry
You might be reading other sites and see lots of posts on ELO models this post isn’t about building an ELO model yourself that’s another post. This post is about how to apply Bradley Terry models for AFL Why Bother? Each of the 18 footy teams plays 22 games a year, we can see who has played who and who won each game. We could just use the AF...
2365 sym R (3631 sym/3 pcs)
But We Won Everywhere but the Scoreboard
Something that gets to many a footy fan, is the feeling that your team has won the game in most areas expect on the scoreboard. Thinking about this statement a little bit deeper has the following implication. That there are some areas of the game, that if you win, you tend to win the game. We can think about this by putting it into a model. The d...
4614 sym R (23781 sym/11 pcs)