November 10, 2020

Mitre 10 Cup Predictions for Round 10

By

Team Ratings for Round 10

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
Tasman 12.46 15.13 -2.70
Auckland 8.56 6.75 1.80
Canterbury 6.80 8.40 -1.60
Bay of Plenty 5.94 8.21 -2.30
Wellington 5.44 6.47 -1.00
North Harbour 5.26 2.87 2.40
Waikato 2.84 1.31 1.50
Hawke’s Bay 2.77 0.91 1.90
Otago -2.59 -4.03 1.40
Taranaki -3.26 -4.42 1.20
Northland -7.87 -8.71 0.80
Southland -10.33 -14.04 3.70
Counties Manukau -11.20 -8.18 -3.00
Manawatu -14.70 -10.57 -4.10

 

Performance So Far

So far there have been 63 matches played, 40 of which were correctly predicted, a success rate of 63.5%.
Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Southland vs. Otago Nov 06 32 – 15 -7.80 FALSE
2 Auckland vs. Northland Nov 07 24 – 20 21.70 TRUE
3 North Harbour vs. Counties Manukau Nov 07 32 – 5 18.20 TRUE
4 Tasman vs. Canterbury Nov 07 0 – 29 13.50 FALSE
5 Hawke’s Bay vs. Wellington Nov 08 34 – 18 -2.00 FALSE
6 Waikato vs. Bay of Plenty Nov 08 30 – 33 0.50 FALSE
7 Manawatu vs. Taranaki Nov 08 19 – 35 -7.20 TRUE

 

Predictions for Round 10

Here are the predictions for Round 10. 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 Counties Manukau vs. Southland Nov 13 Counties Manukau 2.10
2 Northland vs. Waikato Nov 14 Waikato -7.70
3 Otago vs. Tasman Nov 14 Tasman -12.00
4 Wellington vs. Manawatu Nov 14 Wellington 23.10
5 Bay of Plenty vs. North Harbour Nov 15 Bay of Plenty 3.70
6 Taranaki vs. Hawke’s Bay Nov 15 Hawke’s Bay -3.00
7 Canterbury vs. Auckland Nov 15 Canterbury 1.20

 

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
    Samuel Saulep

    David,

    You got 6 out 7, that is remarkable.

    How do you do it? Home team rating? Home ground advantage value?

    4 years ago

    • avatar
      David Scott

      The only information I use is past results, specifically the margin between the two teams and a value for the home ground advantage. The method is the error correction form of exponential smoothing. There are a couple of tweaks to modify the distribution of marginal values to make it close to normal (it is heavy tailed in reality), and the possibility of shrinking of ratings between seasons. There are a number of parameters to be estimated (smoothing parameter and home ground advantage are two obvious ones) which I do via a large grid search (over about 30.000 values in most cases) using a number of years of past data.

      What is important is that exponential smoothing is a great forecasting method: simple enough to be taught to first year undergraduates; requires minimal data and has been shown in forecasting competitions to be highly competitive with much more sophisticated methods.

      A word of warning though. I think I only got 3 correct last week. What is important is long run performance, that is the measure of how good any method is.

      4 years ago