March 9, 2012

Super 15 Predictions, Week 3

By

Team Ratings for Week 3

Here are the team ratings prior to Week 3, 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
Crusaders 9.22 10.46
Bulls 6.38 4.16
Stormers 6.03 6.59
Reds 4.90 5.03
Waratahs 4.35 4.98
Blues 1.78 2.87
Sharks 1.66 0.87
Chiefs -0.95 -1.17
Hurricanes -2.05 -1.90
Highlanders -3.57 -5.69
Force -4.08 -4.95
Cheetahs -4.45 -1.46
Brumbies -6.72 -6.66
Lions -10.12 -10.82
Rebels -15.68 -15.64

 

Performance So Far

So far there have been 14 matches played, 9 of which were correctly predicted, a success rate of 64.3%.

Here are the predictions for the games so far.

Game Date Score Prediction Correct
1 Blues vs. Crusaders Feb 24 18 – 19 -3.10 TRUE
2 Brumbies vs. Force Feb 24 19 – 17 2.80 TRUE
3 Bulls vs. Sharks Feb 24 18 – 13 7.80 TRUE
4 Chiefs vs. Highlanders Feb 25 19 – 23 9.00 FALSE
5 Waratahs vs. Reds Feb 25 21 – 25 4.40 FALSE
6 Stormers vs. Hurricanes Feb 25 39 – 26 13.00 TRUE
7 Lions vs. Cheetahs Feb 25 27 – 25 -4.90 FALSE
8 Chiefs vs. Blues Mar 02 29 – 14 -0.70 FALSE
9 Rebels vs. Waratahs Mar 02 19 – 35 -15.40 TRUE
10 Lions vs. Hurricanes Mar 02 28 – 30 -3.90 TRUE
11 Highlanders vs. Crusaders Mar 03 27 – 24 -10.40 FALSE
12 Reds vs. Force Mar 03 25 – 20 15.10 TRUE
13 Cheetahs vs. Bulls Mar 03 19 – 51 -1.40 TRUE
14 Stormers vs. Sharks Mar 03 15 – 12 10.00 TRUE

 

Predictions for Week 3

Here are the predictions for Week 3. 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 Crusaders vs. Chiefs Mar 09 Crusaders 14.70
2 Force vs. Hurricanes Mar 09 Force 2.50
3 Brumbies vs. Cheetahs Mar 10 Brumbies 2.20
4 Highlanders vs. Waratahs Mar 10 Waratahs -3.40
5 Reds vs. Rebels Mar 10 Reds 25.10
6 Sharks vs. Lions Mar 10 Sharks 16.30
7 Bulls vs. Blues Mar 10 Bulls 9.10


 

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
    James Spray

    Interesting read, but you didn’t take into account the Chiefs having home advantage this weekend despite it being a Crusaders home game.

    Also do you have different constants for different home advantages? For example an NZ team playing an away game in NZ should be more likely to win than playing an away game in South Africa at altitude.

    Unfortunately there are numerous psychological factors in rugby I have observed over the years that most statistically based predictons do not take into account. For example, I bet the Blues will come close to if not beat the Bulls this weekend despite the 9.10 prediction. This is because the Blues can not afford to go 0/3, while the Bulls are 2/2 and don’t need to win this game nearly as much.

    13 years ago

  • avatar
    David Scott

    You are correct about one thing certainly: I did not take account of the venue for the Crusaders v Chiefs. I think I should have made it a neutral venue though rather than a home game for the Chiefs. Hawkes Bay is in the Hurricanes franchise area, not the Chiefs’. Neither choice would have changed my choice of winner however, only the suggested margin.

    I was of the same opinion as you previously that the home ground advantage might be more for South African teams, particularly when playing New Zealand teams. However when I investigated it, I could not see it. It should be noted also though that it is quite hard to choose a value for home ground advantage. I try and choose parameter values which look to be robust.

    As to psychological factors, yes fine, but what value are you going to put on the psychological factor for a given game? My predictions are entirely data based. That is the point. Data based prediction with no subjective element or knowledge of the game is as least as good as the tipping of people classed as experts.

    Another view is that my predictions give a very good idea of what past form says about the likely performance of teams. If you think there are special circumstances pertaining in a particular game, you might wish to deviate from what my predictions say, but my predictions should be a very good starting point.

    The final point is that the result of rugby (and other) games has a very high random component. Anybody who thinks they can predict rugby with an accuracy much above 70% in a league such as Super Rugby is in my view misguided.

    13 years ago

    • avatar
      James Spray

      When you investigated the away games in South Africa vs away games in NZ, did you take into account the strength of the teams? The Lions and Cheetahs are consistently weaker than the weakest NZ teams, and NZ teams often beat them regardless of where the games are played. You are probably right, but I will have a look myself out of interest.

      As for psychological factors – you have already assigned a value for the biggest of them all: the home advantage. I’m sure with a lot of education, knowledge and time, a few more could be taken into account. Unfortunately I don’t have much of any that.

      I was good with that Blues pick though, right? ;)

      13 years ago