NRL Predictions for Round 6
Team Ratings for Round 6
The basic method is described on my Department home page. Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.
| Current Rating | Rating at Season Start | Difference | |
|---|---|---|---|
| Storm | 12.57 | 16.73 | -4.20 |
| Panthers | 4.33 | 2.64 | 1.70 |
| Dragons | 4.23 | -0.45 | 4.70 |
| Sharks | 1.74 | 2.20 | -0.50 |
| Roosters | 1.39 | 0.13 | 1.30 |
| Cowboys | 0.80 | 2.97 | -2.20 |
| Raiders | 0.43 | 3.50 | -3.10 |
| Broncos | 0.31 | 4.78 | -4.50 |
| Wests Tigers | -0.22 | -3.63 | 3.40 |
| Sea Eagles | -0.36 | -1.07 | 0.70 |
| Warriors | -1.32 | -6.97 | 5.70 |
| Rabbitohs | -2.07 | -3.90 | 1.80 |
| Eels | -4.24 | 1.51 | -5.80 |
| Bulldogs | -4.48 | -3.43 | -1.10 |
| Knights | -7.65 | -8.43 | 0.80 |
| Titans | -7.78 | -8.91 | 1.10 |
Performance So Far
So far there have been 40 matches played, 21 of which were correctly predicted, a success rate of 52.5%.
Here are the predictions for last week’s games.
| Game | Date | Score | Prediction | Correct | |
|---|---|---|---|---|---|
| 1 | Raiders vs. Bulldogs | Apr 05 | 26 – 10 | 6.60 | TRUE |
| 2 | Sharks vs. Roosters | Apr 06 | 10 – 28 | 6.80 | FALSE |
| 3 | Dragons vs. Rabbitohs | Apr 06 | 16 – 12 | 10.20 | TRUE |
| 4 | Wests Tigers vs. Storm | Apr 07 | 11 – 10 | -15.00 | FALSE |
| 5 | Warriors vs. Cowboys | Apr 07 | 22 – 12 | 1.10 | TRUE |
| 6 | Knights vs. Broncos | Apr 07 | 15 – 10 | -6.60 | FALSE |
| 7 | Titans vs. Sea Eagles | Apr 08 | 32 – 20 | -7.10 | FALSE |
| 8 | Eels vs. Panthers | Apr 08 | 6 – 12 | -5.50 | TRUE |
Predictions for Round 6
Here are the predictions for Round 6. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.
| Game | Date | Winner | Prediction | |
|---|---|---|---|---|
| 1 | Roosters vs. Rabbitohs | Apr 12 | Roosters | 6.50 |
| 2 | Storm vs. Knights | Apr 13 | Storm | 23.20 |
| 3 | Dragons vs. Sharks | Apr 13 | Dragons | 5.50 |
| 4 | Warriors vs. Broncos | Apr 14 | Warriors | 2.90 |
| 5 | Cowboys vs. Bulldogs | Apr 14 | Cowboys | 8.30 |
| 6 | Raiders vs. Eels | Apr 14 | Raiders | 7.70 |
| 7 | Panthers vs. Titans | Apr 15 | Panthers | 15.10 |
| 8 | Sea Eagles vs. Wests Tigers | Apr 15 | Sea Eagles | 2.90 |
David Scott obtained a BA and PhD from the Australian National University and then commenced his university teaching career at La Trobe University in 1972. He has taught at La Trobe University, the University of Sheffield, Bond University and Colorado State University, joining the University of Auckland, based at Tamaki Campus, in mid-1995. He has been Head of Department at La Trobe University, Acting Dean and Associate Dean (Academic) at Bond University, and Associate Director of the Centre for Quality Management and Data Analysis at Bond University with responsibility for Short Courses. He was Head of the Department of Statistics in 2000, and is a past President of the New Zealand Statistical Assocation. See all posts by David Scott »
Having followed your predictions for quite a few years now, it’s interesting to hypothesise about what’s causing the change in predictability this season – especially with pundits predicting a high finish for the Warriors this season.
6 years ago
The start of the season can be hard to predict. I seem to recall that last year the results in the NRL were under 50% early on. The NRL is typically harder to predict than the Super Rugby and I think the Aviva Premiership. It is hard to get above 60% in the NRL whereas I would expect to get over 70% in the rugby competitions. Not sure why, but it has been consistent over a number of years.
I suspect club strengths are more even in league and would have pointed to the points range differences between the different competitions (about 36 in Super Rugby, 20 in NRL at present), except that Aviva Premiership looks about as predictable as Super Rugby but has a smaller points range (about 16) than NRL.
I have toyed with the idea of using different parameters early in the season (larger smoothing constant would be one obvious option, between season shrinkage would be another) but that would require a fair amount of investigation: what parameters might usefully be changed, what constitutes the start of the season, etc.
The model has responded reasonably well to changes in form like that seen in the Warriors this year to the extent that it (incorrectly) predicted a Warriors win against the Broncos, so I am not sure that a lot of parameter tweaking will do much good. In the end, the inescapable fact is that to an important degree the outcome of sporting contests has a random element.
6 years ago
For RL, it would be interesting to plot average(home team ability – away team ability) for each round over time. The competition draw isn’t some random thing but specifically created (I assume) to fulfill some goals – usually to make the games exciting to watch with peak excitement at season end. IE some parts of the competition are going to be harder to predict by design.
6 years ago