Scoring Shots: Not Just Another Statistic

For a while now I've harboured a suspicion that teams that trail at a quarter's end but that have had more scoring shots than their opponent have a better chance of winning than teams that trail by a similar amount but that have had fewer scoring shots than their opponent.

Suspicions that are amenable to trial by data have a Constitutional right to their day in court, so let me take you through the evidence.

First, let's look at every game in the history of VFL/AFL ending with last year's Grand Final. The results that we're looking for are in the tables below.

The three tables each summarise the results for the end of one particular quarter. The rows correspond to a team's lead as at the end of that quarter (which is negative if the team trails) and the columns correspond to the difference between a team's scoring shots and the scoring shots of its opponent. The percentage shown is the proportion of wins for teams that were in the position described by the column and row as at the end of the relevant quarter.

So, for example, the 6% in the top left corner of the first table tells us that teams that trailed by 25 points or more at the end of the first quarter and that had registered 13 or more fewer scoring shots than their opponents went on to win only 6% of the time. (For each of the percentages shown draws are counted as half-wins.)

The numbers in the rightmost column show the proportion of times that teams win given particular sized leads at the end of a quarter, and shows exactly what we'd expect and what we've seen before: leading at the end of a quarter is good for a team's chances of ultimate victory and the bigger the lead the better.

The numbers at the foot of the each table show the proportion of times that teams win given particular sized differences between their and their opponent's number of scoring shots. Again, there are no surprises in the results: teams that have registered more scoring shots at the end of any quarter tend to go on to win and the larger the difference between their own and their opponent's number of scoring shots, the more likely it is that they go on to win.

What's interesting though is when you look at teams that trail by a little or that are drawn but that have had more scoring shots than their opponents. These are the numbers I've highlighted using red boxes. In the table for Quarter 1, for example, we see that teams that trail by 1 to 6 points but that have had 1 to 3, or 4 to 6 more scoring shots than their opponents, win 49% of the time. This compares with the overall win rate for teams trailing by 1 to 6 points at quarter-time of just 45%.

Note the predictive power of scoring shot numbers when teams are drawn on points at quarter-time. Sixty percent of the time, the team that's had the greater number of scoring shots goes on to win the game.

Looking next at the results as at half-time we find that teams that trail by 1 to 6 points at half-time but that have registered 4 to 6 more scoring shots than their opponents go on to win 57% of the time. Teams that are level on points at half-time but that have registered 4 to 6 more scoring shots than their opponents go on to win 65% of the time.

The three-quarter time results underscore the importance of leading at the last change as here the proportions considered in the previous paragraph drop to 50% and 54% respectively. Nonetheless, we can say that games that are drawn at the end of any of the first three quarters are more likely to be won by the team that's registered the most scoring shots.

Having completed this analysis I then wondered if the results I'd found for the history of the competition were similar if I looked only at the last 30 seasons (ie from 1980 to 2009).

Here are the results for that period:

Too few games have been drawn at the end of the first, second or third quarters for us to safely draw any conclusions about the relative chances of teams having registered 4 to 6 more scoring shots than their opponents in such games; consequently, I've replaced the calculated percentages with asterisks in each table. The raw data, however, is strongly suggestive that the results we found for the history of the competition for drawn situations also hold for the period 1980 to 2009 - as at the end of the first quarter teams that were drawn but that had kicked 4 to 6 more scoring shots than their opponents went to win 67% of games; for the second and third quarters the equivalent percentages are 70% and 67%.

There is plenty of data to draw conclusions about the situations where teams trail by 1 to 6 points but have kicked 4 to 6 more scoring shots than their opponents. In brief, they win more often than they lose. If they trail at the end of the first quarter they win 55% of the time, if at half-time they win 60% of the time, and if at three-quarter time they win 52% of the time.

Reason alone to take a little more notice not just of the score but of the number of scoring shots too.