NRL Predictions, Round 5
Team Ratings for Round 5
Here are the team ratings prior to Round 5, along with the ratings at the start of the season. I have created a brief description of the method I use for predicting rugby games. Go to my Department home page to see this.
| Current Rating | Rating at Season Start | Difference | |
|---|---|---|---|
| Storm | 11.72 | 9.73 | 2.00 |
| Sea Eagles | 8.46 | 4.78 | 3.70 |
| Rabbitohs | 6.91 | 5.23 | 1.70 |
| Bulldogs | 5.13 | 7.33 | -2.20 |
| Knights | 3.77 | 0.44 | 3.30 |
| Titans | 3.54 | -1.85 | 5.40 |
| Cowboys | 1.87 | 7.05 | -5.20 |
| Broncos | -0.77 | -1.55 | 0.80 |
| Roosters | -1.28 | -5.68 | 4.40 |
| Dragons | -1.85 | -0.33 | -1.50 |
| Sharks | -2.29 | -1.78 | -0.50 |
| Raiders | -3.44 | 2.03 | -5.50 |
| Wests Tigers | -5.46 | -3.71 | -1.80 |
| Panthers | -6.88 | -6.58 | -0.30 |
| Eels | -11.25 | -8.82 | -2.40 |
| Warriors | -11.91 | -10.01 | -1.90 |
Performance So Far
So far there have been 32 matches played, 22 of which were correctly predicted, a success rate of 68.75%.
Here are the predictions for last week’s games.
| Game | Date | Score | Prediction | Correct | |
|---|---|---|---|---|---|
| 1 | Sea Eagles vs. Wests Tigers | Mar 28 | 26 – 0 | 16.52 | TRUE |
| 2 | Bulldogs vs. Rabbitohs | Mar 29 | 12 – 17 | 4.65 | FALSE |
| 3 | Broncos vs. Storm | Mar 29 | 26 – 32 | -8.49 | TRUE |
| 4 | Sharks vs. Dragons | Mar 30 | 12 – 25 | 8.33 | FALSE |
| 5 | Panthers vs. Titans | Mar 31 | 10 – 28 | -2.90 | TRUE |
| 6 | Knights vs. Raiders | Mar 31 | 28 – 12 | 10.64 | TRUE |
| 7 | Warriors vs. Cowboys | Apr 01 | 20 – 18 | -12.11 | FALSE |
| 8 | Roosters vs. Eels | Apr 01 | 50 – 0 | 5.59 | TRUE |
Predictions for Round 5
Here are the predictions for Round 5. 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 | Bulldogs vs. Sea Eagles | Apr 05 | Bulldogs | 1.20 |
| 2 | Titans vs. Broncos | Apr 05 | Titans | 8.80 |
| 3 | Eels vs. Sharks | Apr 06 | Sharks | -4.50 |
| 4 | Cowboys vs. Panthers | Apr 06 | Cowboys | 13.30 |
| 5 | Dragons vs. Knights | Apr 07 | Knights | -1.10 |
| 6 | Warriors vs. Rabbitohs | Apr 07 | Rabbitohs | -14.30 |
| 7 | Raiders vs. Roosters | Apr 07 | Raiders | 2.30 |
| 8 | Storm vs. Wests Tigers | Apr 08 | Storm | 21.70 |
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 »
Hello David Scott, i was just wondering what method you are using for these predictions as i have also been quite interested in the success rate of stats in determining the outcome of future sporting fixtures? Currently i’m using dominance matrices for NRL and have around a 80% success rate coming into round 4. I’m interested in your method as i use my predictions to fund my uni expenses and would like to improve on my method. I also have around $500 invested in my tipping fund and make around $180 a week.
11 years ago
My method is explained on my home page as it says at the top of each post. It is exponential smoothing.
How can I say this nicely? I don’t believe there is any possible way anyone can consistently predict NRL games with anything like 80% accuracy. My experience is that mid 60’s is very good and I have had that opinion expressed by others also. If I recall correctly, an article I read suggested that for most sports, predictability of games would typically not be much more than 70%.
I have some particular concerns about dominance matrices as a method of prediction. How do you weight more recent results compared to past results? Surely recent form is the most relevant. Do you have some sort of rolling weighting only considering some given number of past games? How do you incorporate home ground advantage? Most studies have found it exists. Dominance matrices are non-parametric essentially in that they do not consider the winning margin. How then do you obtain a probability that a given side wins, which is what is needed for betting. Finally, it seems someone has patented the use of dominance matrices for prediction, or at least tried to: http://www.google.com/patents/US20120197904. Mind you, I think that is ridiculous given the widespread prior use of dominance matrices.
As to earning $180 regularly with a bank of $500, I don’t know how much you are investing, but generally the use of a fractional Kelly criterion is wise to avoid the risk of your stake being wiped out through a run of adverse results. See http://en.wikipedia.org/wiki/Kelly_criterion
11 years ago