March 27, 2014

Super 15 Predictions for Round 7

Team Ratings for Round 7

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
Sharks 6.23 4.57 1.70
Crusaders 6.07 8.80 -2.70
Chiefs 4.72 4.38 0.30
Brumbies 4.45 4.12 0.30
Waratahs 4.38 1.67 2.70
Bulls 4.20 4.87 -0.70
Stormers 1.68 4.38 -2.70
Reds -0.48 0.58 -1.10
Hurricanes -0.57 -1.44 0.90
Blues -1.59 -1.92 0.30
Highlanders -3.50 -4.48 1.00
Cheetahs -3.66 0.12 -3.80
Lions -3.94 -6.93 3.00
Force -4.07 -5.37 1.30
Rebels -6.93 -6.36 -0.60

 

Performance So Far

So far there have been 36 matches played, 24 of which were correctly predicted, a success rate of 66.7%.

Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Highlanders vs. Hurricanes Mar 21 35 – 31 -1.10 FALSE
2 Waratahs vs. Rebels Mar 21 32 – 8 12.40 TRUE
3 Blues vs. Cheetahs Mar 22 40 – 30 5.40 TRUE
4 Brumbies vs. Stormers Mar 22 25 – 15 6.20 TRUE
5 Force vs. Chiefs Mar 22 18 – 15 -5.90 FALSE
6 Lions vs. Reds Mar 22 23 – 20 0.10 TRUE
7 Bulls vs. Sharks Mar 22 23 – 19 -0.10 FALSE

 

Predictions for Round 7

Here are the predictions for Round 7. 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 Crusaders vs. Hurricanes Mar 28 Crusaders 9.10
2 Rebels vs. Brumbies Mar 28 Brumbies -8.90
3 Blues vs. Highlanders Mar 29 Blues 4.40
4 Reds vs. Stormers Mar 29 Reds 1.80
5 Bulls vs. Chiefs Mar 29 Bulls 3.50
6 Sharks vs. Waratahs Mar 29 Sharks 5.90

 

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
    Werner Brink

    Hi David,

    I have been dabbling in the predictions of Super rugby games this year as well. Even built a rudimentary prediction model which includes a rating system. However I’m curious as to what you based your rating system on. Or rather how did you come to your parameters that you used to determine the rating?

    11 years ago

    • avatar

      I look at what parameter values have worked well in previous seasons. There is great variation in the optimal parameter values, so I try to chose values which have given good results over a number of seasons.

      11 years ago

  • avatar
    Quintus van der Berg

    Hi Prof Scott

    I have been following your prediction stats for Super Rugby since I joined Superbru last year.

    It inspired me to build my own prediction model, which has served me well so far.

    I have noted that we sometimes come up with different predictions and, over the past year and a bit, mine seemed to be more often correct. This might be just beginners luck.

    However, I think I have narrowed it down to an “unexpected loss” multiplier that I have built into my system. It basically rests on a comment attributed to the late Dr Danie Craven (long time president of SA Rugby) that “the team that lost most recently, is most likely to win the final”.

    I refined it to an “upset loss”, i.e. that if a team loses unexpectedly they are more likely to perform above their prevailing form and overall quality level the following week.

    I would really appreciate your thoughts on this and also if and how you might have factored this into your own system already.

    Kind Regards

    Q

    11 years ago

    • avatar

      Well first of all I would like to see some statistical evidence for such an effect. Then I would have to decide what constitutes an “unexpected loss”, and decide on an operational definition. Finally I would need to estimate the factor involved. Once I had done all those things I could add it to my system. You should be aware that I do totally data-based predictions, and eschew subjective decisions as far as possible. Your idea is interesting, but I am not likely to investigate it in the near future.

      11 years ago

  • avatar
    Del Jacobs

    Could “unexpected loss” be the flip-side of “unexpected win”?

    11 years ago

    • avatar
      Quintus van der Berg

      Nope, an unexpected win would carry momentum and have the same positive effect on form as the motivation a team gets from an unexpected loss…in my opinion anyway :-)

      11 years ago

      • avatar
        Del Jacobs

        So, in your model, both teams “benefit” motivation-wise from an “unexpected-win”?

        11 years ago