Grand Final Typology

Today's blog looks at the typology of AFL Grand Finals.

There are, it turns out, five basic types:
(1) The Coast-to-Coast Coasting victory
(2) The Come-From-Behind victory
(3) The Game-of-Two-Halves Victory
(4) The Coast-to-Coast Blowout Victory
(5) The Nervous Start Victory

Here's a little more on each type:

(1) The Coast-to-Coast Coasting victory

The key characteristic of this Grand Final type is that the winning team tends to lead at every change, but not by much.

There have been 31 Grand Finals of this type in history, the most recent in 2006 when West Coast led against the Swans at every change and clung on to win by a point. The Grand Final of the previous year is another example of this type; in that case the Swans led at every change over the Eagles.

(2) The Come-From-Behind victory

The key characteristic of this Grand Final type is that the winning team tends to trail at every change.

There have been only 7 instances of this type of Grand Final, the most recent in 1984 when Hawthorn led at every change before Essendon swamped them win a 9.6 to 2.1 final term.

The famous 1970 GF when Carlton kicked 5.4 to Collingwood's 1.1 in the final term to complete a stunning victory is another example of this type.

(3) The Game-of-Two-Halves Victory

The key characteristic of this Grand Final type is that the winning team tends to lead at quarter time, trails at half time but wrests the lead by three-quarter time and doesn't surrender it.

There have been 20 Grand Finals of this type in history. The GF of 2004 is an example of this type. In that year Port Adelaide led Brisbane 4.5 to 2.2 at quarter time, trailed 6.6 to 6.7 at half time, led 12.8 to 9.9 at three-quarter time, and went on to win 17.11 to 10.13.

(4) The Coast-to-Coast Blowout Victory

The key characteristic of this Grand Final type is that the winning team leads going away at every quarter.

History has produced 33 of these GF types, probably none of them good to watch for any except the fans of the winning team.

2007 leaps immediately to mind and is, unsurprisingly a GF of this type. In that year Geelong led by 23 points at quarter time, 52 points at half time, 90 points at three-quarter time, and 119 points at the final siren.

(5) The Nervous Start Victory

The key characteristic of this Grand Final type is that the winning team trails at quarter time but generally at none of the changes thereafter.

There have been 19 GFs of this type, including last year's fare. In that game the Hawks trailed the Cats by 1 point at the first change then steadied to lead by 3 points and then 17 points at the second and third changes. They won, eventually, by 26 points.

Where, you might ask, did I come up with all this?

Well, I didn't make this typology up. It came as a result of an analysis of Grand Final data using a technique called cluster analysis which, in essence, is a statistical technique that allows you to group things based on how similar they are.

To use the technique you need to decide the data on which you'll assess similarity and you need to choose what's called a "distance metric", which is the mathematical way by which you'll convert differences in the raw data into measures of similarity.

The data I used to come with these clusters was fairly simple: which team - the eventual winner or loser - led at each change, and what the eventual winning team's margin was at half time and at full time. If you want to read up on the technical details, I used pam clustering and the gower distance metric.

Now not every Grand Final fits one of these 5 descriptions perfectly, but each Grand Final is, in a mathematical sense, closer to one of these 5 types than to any of the others. That allows me to classify each of the 110 Grand Finals we've had so far.

The summary of that classification appears in this next table: 

Scanning the rightmost 4 columns you can see how the mix of GF types has varied across the four epochs I've used: 1897-1919, 1920-1949, 1950-1979, and 1980-2008.

The period 1897-1919 was the heyday of the Coast-to-Coast Coasting Victory. Ten examples of this GF type came in that era.

Subsequently, the 1920-1949 era was dominated by the Coast-to-Coast Coasting Victory and the Coast-to-Coast Blowout Victory types. Combined these accounted for 18 of the 29 GFs in that period.

The 1950-1979 era was fairly similar to the 1920-1949 era though with a slightly higher proportion of Coast-to-Coast Coasting Victory types and a slightly lower proportion of Coast-to-Coast Blowout Victory types.

But, unfortunately, the Coast-to-Coast Blowout Victory wasn't really going away. It has dominated the GFs since 1980, providing 12 of the 29 results. This period has also produced 7 Nervous Start Victory type GFs, which represents the largest proportion of this type for any era.

The technique I use also spits out what it considers to be the 'best' example of each type of GF, a summary of which appears below:

As soon as I have time I'll be providing a graphic showing the typology of every Grand Final so far including the 2009 GF (so I guess you won't be getting it before Sunday at least) ...

... Okay, as it turned out I had a little time this evening so I created the table showing the classification of every Grand Final a little earlier than I expected. It's available as a download here

The Grand Finals are sorted firstly by type and then, within type, by their similarity to the archetypical Grand Final of that type. The rightmost column provides a measure of this similarity - the smaller the number the closer that Grand Final is to the archetypical Grand Final. I've colour-coded the archetypical Grand Finals grey and those Grand Finals that are relatively 'close to' the relevant archetypical Grand Final in green.

So, for example, consider the second GF block in Coast-to-Coast Coasting. It's for the 1912 GF and shows Essendon defeating South Melbourne, leading 10-9 at QT, 27-16 at HT, 38-18 at 3QT and 47-33 at FT. It's very similar to the 1910 GF, which is the archetypical Coast-to-Coast Coasting GF.

Enjoy. 

Comments

[Mitch]

You're probably sick of it (so put it on the to-do list), but do you think there might be a relationship between the relative difference in the GF teams' MARS ratings and the GF typology? (e.g.large MARS disparities produce coast-to-coast blowouts?)

[TC]

Your hypothesis has a lot to recommend it.

To test it I'll need to build a script to generate MARS ratings for the history of the VFL/AFL. That definitely sounds like a job for the off-season.