Super 15 Predictions for Round 3
Team Ratings for Round 3
The basic method is described on my Department home page. I have made some changes to the methodology this year, including shrinking the ratings between seasons.
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 | |
|---|---|---|---|
| Crusaders | 7.89 | 8.80 | -0.90 |
| Sharks | 5.84 | 4.57 | 1.30 |
| Chiefs | 5.29 | 4.38 | 0.90 |
| Bulls | 3.55 | 4.87 | -1.30 |
| Brumbies | 3.15 | 4.12 | -1.00 |
| Stormers | 2.56 | 4.38 | -1.80 |
| Waratahs | 2.44 | 1.67 | 0.80 |
| Reds | 1.56 | 0.58 | 1.00 |
| Cheetahs | -0.02 | 0.12 | -0.10 |
| Hurricanes | -1.91 | -1.44 | -0.50 |
| Blues | -2.44 | -1.92 | -0.50 |
| Highlanders | -3.96 | -4.48 | 0.50 |
| Lions | -4.45 | -6.93 | 2.50 |
| Force | -6.14 | -5.37 | -0.80 |
| Rebels | -6.36 | -6.36 | -0.00 |
Performance So Far
So far there have been 9 matches played, 3 of which were correctly predicted, a success rate of 33.3%.
Here are the predictions for last week’s games.
| Game | Date | Score | Prediction | Correct | |
|---|---|---|---|---|---|
| 1 | Crusaders vs. Chiefs | Feb 21 | 10 – 18 | 6.90 | FALSE |
| 2 | Cheetahs vs. Bulls | Feb 21 | 15 – 9 | -2.10 | FALSE |
| 3 | Highlanders vs. Blues | Feb 22 | 29 – 21 | -0.10 | FALSE |
| 4 | Brumbies vs. Reds | Feb 22 | 17 – 27 | 6.00 | FALSE |
| 5 | Sharks vs. Hurricanes | Feb 22 | 27 – 9 | 10.80 | TRUE |
| 6 | Lions vs. Stormers | Feb 22 | 34 – 10 | -8.10 | FALSE |
| 7 | Waratahs vs. Force | Feb 23 | 43 – 21 | 9.50 | TRUE |
Predictions for Round 3
Here are the predictions for Round 3. 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 | Blues vs. Crusaders | Feb 28 | Crusaders | -7.80 |
| 2 | Rebels vs. Cheetahs | Feb 28 | Cheetahs | -2.30 |
| 3 | Stormers vs. Hurricanes | Feb 28 | Stormers | 8.50 |
| 4 | Chiefs vs. Highlanders | Mar 01 | Chiefs | 11.70 |
| 5 | Waratahs vs. Reds | Mar 01 | Waratahs | 3.40 |
| 6 | Force vs. Brumbies | Mar 01 | Brumbies | -6.80 |
| 7 | Bulls vs. Lions | Mar 01 | Bulls | 10.50 |
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 »
I think you are making a mistake wtiht eh Bulls and the Stormers.You hsould take into account the losses a team gets. Say for instance the Stormers loses to the Lions that lost hould be considered and the amount of points they lose with..Also add a point for momentum. If the Chiefs have won the previous game they are on a upwards graph and therefore they should get a xtra point. Momentum is a big thing in sport.
11 years ago
Have you looked at the changes in rankings over the season? The Stormers have gone down by almost two points, the Bulls by 1.3, after only two games. The Chiefs have gone up nearly a point after a single game. What you are saying amounts to the belief that I am not weighting recent results sufficiently heavily. That may be the case for this season, and for early in the season because it is actually quite difficult to choose the model parameters at the start of each season. I have investigated adaptive exponential smoothing methods where the parameters adjust based on the data. Early proposals for adaptive exponential smoothing were found to have poor forecasting properties, but more recent proposals are more promising. I would like some more experience though before I take such an approach.
11 years ago
So many variables at the team level – still not a good weekend, including the huge margins on the “True’s” – something needs tweaking…
11 years ago
Difficult week for forecasting. Some unlikely winners and the close games went the other way to my predictions.
11 years ago