October 9, 2018

Mitre 10 Cup Predictions for Round 9

Team Ratings for Round 9

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
Canterbury 14.38 15.32 -0.90
Wellington 12.22 12.18 0.00
Tasman 8.59 2.62 6.00
Waikato 8.04 -3.24 11.30
North Harbour 6.47 6.42 0.10
Auckland 6.18 -0.50 6.70
Otago -1.22 0.33 -1.50
Counties Manukau -2.77 1.84 -4.60
Taranaki -3.77 6.58 -10.30
Bay of Plenty -4.72 0.27 -5.00
Northland -6.24 -3.45 -2.80
Hawke’s Bay -6.30 -13.00 6.70
Manawatu -11.44 -4.36 -7.10
Southland -21.60 -23.17 1.60

 

Performance So Far

So far there have been 62 matches played, 43 of which were correctly predicted, a success rate of 69.4%.
Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Otago vs. Bay of Plenty Oct 03 45 – 34 8.30 TRUE
2 Wellington vs. Auckland Oct 04 24 – 29 13.30 FALSE
3 Hawke’s Bay vs. Manawatu Oct 05 45 – 17 5.00 TRUE
4 Northland vs. Waikato Oct 06 28 – 71 -3.10 TRUE
5 North Harbour vs. Counties Manukau Oct 06 36 – 26 14.00 TRUE
6 Canterbury vs. Taranaki Oct 06 41 – 7 19.50 TRUE
7 Southland vs. Bay of Plenty Oct 07 22 – 26 -15.10 TRUE
8 Otago vs. Tasman Oct 07 21 – 47 -1.60 TRUE

 

Predictions for Round 9

Here are the predictions for Round 9. 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 Southland vs. Auckland Oct 10 Auckland -23.80
2 Tasman vs. Hawke’s Bay Oct 11 Tasman 18.90
3 Taranaki vs. Wellington Oct 12 Wellington -12.00
4 Bay of Plenty vs. Northland Oct 13 Bay of Plenty 5.50
5 Waikato vs. Otago Oct 13 Waikato 13.30
6 Counties Manukau vs. Canterbury Oct 13 Canterbury -13.10
7 Auckland vs. North Harbour Oct 14 Auckland 3.70
8 Manawatu vs. Southland Oct 14 Manawatu 14.20

 

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
    Brian alain

    HI thanks for your prediction.

    I would like to make prediction with your method for rugbyTOP14 but i don’t know where i suppose to start, do you have like software or can you give me some tips :)

    thanks a lot

    6 years ago

    • avatar

      The application of exponential smoothing to this problem is due to Stephen Clarke from Swinburne University and he has published a number of papers about it.

      To implement the method there are a number of problems.

      First up, you need a few years of data from the competition to create initial rating estimates. You have to obtain that data and reformat it so it is usable.

      You obviously need to write some code to implement the method. You could use a spreadsheet but that has limitations.

      Then you need to estimate some parameters. That can take some judgement when you have multiple parameters. (I have up to 6.)

      Once results come in you need to add them to your data and update your ratings. I used to enter new results by hand which is time-consuming and error prone. I now have code to scrape results from the web and update my data each week for a number of competitions.

      Most recently I have been able to scrape results from a single location for a number of competitions. There can still be a lot of messy code to format the scraped data (60 lines of code in my case for one competition).

      My aim is for any competition I wish to forecast, I can produce updated forecasts simply by changing the round number I want to forecast and running my programs. I am nearly at that point now having overcome what I saw as the last substantial hurdle.

      Part of the reason for doing that work is that I wish to forecast a number of European competitions: the English Rugby Premiership, the Pro14 and the European Champions Cup.

      Earlier this year I gave predictions for the Rugby Premiership and I hope to have predictions for that competition for this season (2018 – 2019) perhaps by the end of this week.

      6 years ago

  • avatar
    Lee Campbell

    Why is the southland vs bay of plenty prediction true?

    6 years ago

    • avatar

      Because a negative value for the predicted difference means the away team was predicted to win, which in this case was Bay of Plenty. Hence a correct prediction.

      6 years ago