September 24, 2019

Rugby World Cup Predictions 2

By

I was hoping to be able to release predictions in batches of 8 matches, but some matches which could be predicted already would then not have a prediction. Instead I have decided to predict all future games, and update as required to ensure that before a team plays, my predictions will take into account all previous games.

Observe below that means for example that I will provide updated predictions before the Georgia vs. Uruguay game to take into account the game played by Uruguay against Fiji.

Team Ratings 2

The basic method is described on my Department home page.
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
New Zealand 27.68 27.60 0.10
England 19.04 19.78 -0.70
South Africa 18.42 18.51 -0.10
Ireland 13.68 12.12 1.60
Wales 12.62 12.72 -0.10
Australia 9.06 8.70 0.40
France 7.02 7.11 -0.10
Argentina 4.23 4.15 0.10
Scotland 3.88 5.44 -1.60
Fiji -5.64 -5.27 -0.40
Japan -9.08 -7.67 -1.40
Italy -9.31 -8.57 -0.70
Samoa -11.89 -11.89 -0.00
USA -16.38 -16.38 -0.00
Georgia -17.32 -17.43 0.10
Tonga -19.72 -20.46 0.70
Canada -32.45 -32.45 0.00
Russia -35.38 -36.78 1.40
Uruguay -35.67 -35.67 -0.00
Namibia -41.06 -41.80 0.70

 

Performance So Far

So far there have been 8 matches played, 8 of which were correctly predicted, a success rate of 100%.
Here are the predictions for the previous games.

Game Date Score Prediction Correct
1 Japan vs. Russia Sep 20 30 – 10 35.60 TRUE
2 Australia vs. Fiji Sep 21 39 – 21 14.00 TRUE
3 France vs. Argentina Sep 21 23 – 21 3.00 TRUE
4 New Zealand vs. South Africa Sep 21 23 – 13 9.10 TRUE
5 Italy vs. Namibia Sep 22 47 – 22 33.20 TRUE
6 Ireland vs. Scotland Sep 22 27 – 3 6.70 TRUE
7 England vs. Tonga Sep 22 35 – 3 40.20 TRUE
8 Wales vs. Georgia Sep 23 43 – 14 30.10 TRUE

 

Predictions 2

Here are the updated predictions. 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 Russia vs. Samoa Sep 24 Samoa -23.50
2 Fiji vs. Uruguay Sep 25 Fiji 30.00
3 Italy vs. Canada Sep 26 Italy 23.10
4 England vs. USA Sep 26 England 35.40
5 Argentina vs. Tonga Sep 28 Argentina 24.00
6 Japan vs. Ireland Sep 28 Ireland -16.30
7 South Africa vs. Namibia Sep 28 South Africa 59.50
8 Georgia vs. Uruguay Sep 29 Georgia 18.30
9 Australia vs. Wales Sep 29 Wales -3.60
10 Scotland vs. Samoa Sep 30 Scotland 15.80
11 France vs. USA Oct 02 France 23.40
12 New Zealand vs. Canada Oct 02 New Zealand 60.10
13 Georgia vs. Fiji Oct 03 Fiji -11.70
14 Ireland vs. Russia Oct 03 Ireland 49.10
15 South Africa vs. Italy Oct 04 South Africa 27.70
16 Australia vs. Uruguay Oct 05 Australia 44.70
17 England vs. Argentina Oct 05 England 14.80
18 Japan vs. Samoa Oct 05 Japan 9.30
19 New Zealand vs. Namibia Oct 06 New Zealand 68.70
20 France vs. Tonga Oct 06 France 26.70
21 South Africa vs. Canada Oct 08 South Africa 50.90
22 Argentina vs. USA Oct 09 Argentina 20.60
23 Scotland vs. Russia Oct 09 Scotland 39.30
24 Wales vs. Fiji Oct 09 Wales 18.30
25 Australia vs. Georgia Oct 11 Australia 26.40
26 New Zealand vs. Italy Oct 12 New Zealand 37.00
27 England vs. France Oct 12 England 12.00
28 Ireland vs. Samoa Oct 12 Ireland 25.60
29 Namibia vs. Canada Oct 13 Canada -8.60
30 USA vs. Tonga Oct 13 USA 3.30
31 Wales vs. Uruguay Oct 13 Wales 48.30
32 Japan vs. Scotland Oct 13 Scotland -6.50

 

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
    Rikus White

    I think you might be missing 2 games for round 2 here….

    Aus Vs. Wales
    Scotland Vs. Samoa

    Hope to see them here too……

    5 years ago

    • avatar
      Rob Searle

      Looks like games 9 and 10 in the list to me

      5 years ago

  • avatar
    Erik Pretorius

    Thanx for the predictions

    What is your predictions for Aus vs Wales? Round 2 also

    5 years ago

  • avatar
    Jay Brady

    How can you say you predicted all of the games correctly? Most of your predictions are not correct. Especially the Ireland vs Scotland game. The margin is 24 yet you put down 6 and say it’s correct?

    5 years ago

  • avatar
    David Bieleski

    Does TRUE indicate correctly picked the winner or the point differential was within a margin of error?

    Seems to be working well other than in blowout games the model seems to underestimate the margin

    5 years ago

  • avatar
    Jay Sin

    Can someone please explain how the final score is predicated based on the above predictions? Thanks

    5 years ago

    • avatar
      David Scott

      I don’t predict final scores, only the score difference (the margin). So for Argentina vs Tonga, I predict Argentina will win by 24 points. If the margin is negative that means I predict the second team will win, so for Japan vs Ireland, I predict Ireland will win by 16.30 points.

      I give a predicted difference that should be regarded as an indicator of the chance that the team I select will actually win. I say my prediction is TRUE if I get the winning team right, not if I predict the margin to some specified value as required by some betting sites or forecasting competitions.

      Note that the predicted margin is the expected difference and there is uncertainty around that value. In fact the distribution of scores around the expected value is what is called heavy-tailed: there are more extreme values than if the distribution was normal. One manifestation of this is that when a team wins, the margin in many cases can be quite large compared to the predicted margin. On the other hand there can be substantial upsets, e.g. Fiji vs Uruguay where I had a margin on 30 points to Fiji (along with international bookmakers according to one report I read).

      In past Rugby World Cups there have typically been at least a couple of real upsets. Looking at the predictions for the pool games it would seem that only a very few games might be close, but upsets may well still occur in those games.

      5 years ago

  • avatar
    Liam Jack

    Thank you for putting up predictions for multiple weeks, helps me allot.

    5 years ago

  • avatar
    David Bieleski

    Do your predictions account for any homefield advantage for Japan?

    5 years ago