May 9, 2012

Super 15 Predictions, Week 12

Team Ratings for Week 12

Here are the team ratings prior to Week 12, 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
Crusaders 8.44 10.46 -2.00
Stormers 7.60 6.59 1.00
Bulls 6.36 4.16 2.20
Chiefs 3.56 -1.17 4.70
Sharks 0.42 0.87 -0.50
Waratahs -0.46 4.98 -5.40
Reds -0.75 5.03 -5.80
Brumbies -0.92 -6.66 5.70
Hurricanes -1.24 -1.90 0.70
Highlanders -2.39 -5.69 3.30
Cheetahs -2.79 -1.46 -1.30
Blues -3.14 2.87 -6.00
Force -4.75 -4.95 0.20
Lions -10.32 -10.82 0.50
Rebels -12.89 -15.64 2.70

 

Performance So Far

So far there have been 73 matches played, 52 of which were correctly predicted, a success rate of 71.2%.

Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Hurricanes vs. Blues May 04 35 – 19 4.60 TRUE
2 Rebels vs. Bulls May 04 35 – 41 -16.40 TRUE
3 Chiefs vs. Lions May 05 34 – 21 19.40 TRUE
4 Brumbies vs. Waratahs May 05 23 – 6 1.60 TRUE
5 Sharks vs. Highlanders May 05 28 – 16 6.40 TRUE
6 Cheetahs vs. Force May 05 17 – 13 6.90 TRUE
7 Crusaders vs. Reds May 06 15 – 11 15.50 TRUE

 

Predictions for Week 12

Here are the predictions for Week 12. The prediction is my estimated 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. Lions May 11 Blues 11.70
2 Waratahs vs. Bulls May 11 Bulls -2.30
3 Highlanders vs. Hurricanes May 12 Highlanders 3.30
4 Rebels vs. Crusaders May 12 Crusaders -16.80
5 Sharks vs. Force May 12 Sharks 9.70
6 Stormers vs. Cheetahs May 12 Stormers 14.90
7 Reds vs. Chiefs May 13 Reds 0.20

 

avatar

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 »

Comments

  • avatar
    David Spier

    Game 2, rebels vs bulls, prediction of spread of 16.4 for bulls, actual result was spread of 6. Check your excel formula….F9 refresh???

    13 years ago

    • avatar

      I am tempted to say “no Excel was used in the creation of these predictions”, but I do enter the results in a .csv file using Excel. The calculations and the production of the html for creation of the Stats Chat posts are done entirely with R () along with the package hwriter.

      If I understand the import of your comment correctly however, I am quite sanguine about getting a margin wrong: there is such a thing as random variation. I think it is only possible to predict the result of Super 15 games correctly about 70% of the time, and predicting the margin is even harder.

      13 years ago

      • avatar
        David Spier

        I understand! Only predicting the winner, not the margin. Great site too, great stats.

        Makes the rugby betting more fun!

        13 years ago

  • avatar

    Your margin accuracy ( =13) is sitting at 67.1% . Margin prediction can be done by comparing key performance criteria – yet the referee penalty count, key play-makers injured, and teams with a healthy margin taking their peddle off in the last 10 mins can – and will – affect the end result. On the contrary, the bonus point structure for tries & margin can assist.

    13 years ago

  • avatar
    Gary

    Your estimate of predicting games around 70% of the time would seem to correlate with my own human efforts at superbru.com, currently running at 72.6%. I’m curious as to whether the machine will overtake me by the end of the season.

    Do you find that the success rate increases as the season progresses? That is, as the team rating is adjusted by the success of the current years team, from presumably it’s initial estimate probably based on previous years performance.

    13 years ago

    • avatar

      This year I think it was difficult to carry form over from the previous season. There were a large number of changes in the NZ teams at least (Hurricanes, Chiefs, Blues in particular), and what seems to me to be a World Cup hangover effect in some players.

      I am thinking of some tweaks in my methodology next year which may result in quicker response to changes in form early in the season.

      The NRL though was possibly worse with some leading sides from previous years performing badly, and some easybeats from previous years performing well. See the big changes in the ratings of the teams in my tables.

      13 years ago