Glass Blown Open Preview: Win Probabilities

Win, top-5, and top-10 probabilities

The pro-side of the Glass Blown Open — the second PDGA National Tour event of the season — starts tomorrow and we’re starting our preview of the event a little early by introducing win, top-5, and top-10 probabilities.

Glass Blown Open logo. Image: Dynamic Discs

A few months ago we introduced 2017 Elo ratings for the Open and Open Women’s divisions. This week, I am using those ratings1 to estimate win, top-5, and top-10 probabilities for the Glass Blown Open. Unsurprisingly, the model is quite “chalky” at the top: the best players are a small handful. Paul McBeth and Ricky Wysocki have the greatest chances of winning in Open because, well, they are the best,2 and Paige Pierce is the clear favorite in Open Women. Immediately below them, there are not too many surprises with Nate Sexton and Jeremy Koling, and Catrina Allen and Sarah Hokom being the next favorites in their respective divisions.

The tables below show sortable columns containing: current Elo rating, change in Elo rating due to 2017 GBO,3 and Win, Top-5, and Top-10 probabilities (as percentages) for the 20 players in each division with the highest win probabilities.4 For players that have not played in any NT or DGPT events this year or last, their Elo ratings were set at 1500, which is the value I use to start estimating a rating for any player.

PlayerElo RatingChange In EloWin Prob.Top-5 Prob.Top-10 Prob.
Paul McBeth2004.91324.782.993.4
Ricky Wysocki2004.310.922.780.792.5
Nathan Sexton1774.7123.532.957.7
Jeremy Koling1797.783.532.157.1
Simon Lizotte1764.310.9329.153.4
Nathan Doss1784.26.32.82751.1
Paul Ulibarri17905.22.826.750.9
Philo Brathwaite1768.382.626.249.9
Nikko Locastro17855.12.625.749.5
Devan Owens1755.182.323.846.6
Eagle McMahon1723.44.51.415.533.9
Drew Gibson17063.31.112.528.5
JohnE McCray1670.28.8112.628.4
Gregg Barsby1679.95.80.911.526.5
James Conrad1616.58.60.67.818.7
Eric McCabe1629.35.70.67.417.9
Zach Melton1646.31.80.56.816.8
Austin Turner1601.56.60.46.114.9
Chris Clemons1567.4110.45.814.2
Dustin Keegan1628.900.45.213.2
PlayerElo RatingChange In EloWin Prob.Top-5 Prob.Top-10 Prob.
Paige Pierce1708.110.539.899.799.9
Catrina Allen16677.928.598.299.6
Sarah Hokom1618.43.811.282.896.6
Valarie Jenkins1589.33.24.858.490
Jessica Weese1564.22.12.130.876.1
Lisa Fajkus1563.715.11.466.786
Jennifer Allen1559.65.81.636.276.3
Madison Walker15410112.153.7
Zoe Andyke1530.500.78.243.5
Paige Bjerkaas1530.22.60.610.846.6
Melody Waibel1527.90.90.68.342.2
Nicole Bradley1522.400.56.136
Elaine King152200.5635.6
Karina Nowels1518.400.55.232.5
Ellen Widboom1517.200.4531.5
Rebecca Cox1513.80.80.44.829.6
Des Reading1509.87.40.38.433.6
Vanessa Van Dyken1506.200.33.323.1
Nicole Dionisio1503.6-0.30.32.821
Tina Stanaitis1502.7-30.3218.3

To get these predictive probabilities, I used players current Elo ratings and how their ratings changed after the 2017 GBO. In other words, the model uses how a player is playing now (using our most current data), and how the player played in the event the year before.5 For example, Chris Clemons and Lisa Fajkus both finished third last year, and significantly improved their ratings and chances at this years GBO. I also included strength of field in the model.6

When developing models like this it is important to verify their predictive value. You do this using something called cross-validation, where you develop a model using half of the dataset and see how the model does predicting the outcomes using the other half. Using this method, I correctly classified players 96.7-percent, 89-percent, and 82-percent of the time for the winner, top-5, and top-10 portions of the model.7 So, it does pretty well. For example, the model correctly predicted the Open and Open Women’s winners at the Jonesboro Open.8 It also forecast, exactly, the 5th place finish of Dave Feldberg. This prediction was, in part based on his 8th place finish at the tournament last year. A bit more surprisingly, it predicted that Will Schusterick would finish in 11th place, which many observers would have probably considered too high before the event given the injuries he has struggled with recently. He played well and finished 13th, just two strokes out of 11th place.

What these results hopefully indicate is that this predictive model and the associated ratings have some value. They provide an alternative to the ratings and other statistics produced by the PDGA. Also, they are useful when thinking about important factors that influence a player’s chance to win or place well in a tournament (finishing inside the top-5 or top-10).

In that way, it can provide some information regarding players to potentially (like the earlier examples of Clemons, Fajkus, Feldberg and Schusterick show) keep an eye on, beyond those at the very top of the field. We will continue to preview the 2018 GBO by taking a closer look at some of those players to keep on eye on in a second preview article tomorrow.


PlayerElo RatingChange In EloWin Prob.Top-5 Prob.Top-10 Prob.
Paul McBeth2004.91324.782.993.4
Richard Wysocki2004.310.922.780.792.5
Nathan Sexton1774.7123.532.957.7
Jeremy Koling1797.783.532.157.1
Simon Lizotte1764.310.9329.153.4
Nathan Doss1784.26.32.82751.1
Paul Ulibarri17905.22.826.750.9
Philo Brathwaite1768.382.626.249.9
Nikko Locastro17855.12.625.749.5
Devan Owens1755.182.323.846.6
Eagle McMahon1723.44.51.415.533.9
Drew Gibson17063.31.112.528.5
Johne Mccray1670.28.8112.628.4
Gregg Barsby1679.95.80.911.526.5
James Conrad1616.58.60.67.818.7
Eric McCabe1629.35.70.67.417.9
Zach Melton1646.31.80.56.816.8
Austin Turner1601.56.60.46.114.9
Chris Clemons1567.4110.45.814.2
Dustin Keegan1628.900.45.213.2
A.J. Risley1591.85.20.45.112.7
Seppo Paju1622.100.44.912.4
Peter McBride1603.500.34.110.5
Nate Perkins1565.96.40.34.310.9
Henrik Johansen1595.71.20.34.110.5
Eric Oakley1583.63.20.34.110.6
Matt Bell1568.24.70.3410.1
Joel Freeman1560.35.40.33.89.8
Zackeriath Johnson1579.91.40.33.69.3
Austin Hannum1538.67.40.23.69
Jordan Castro1548.95.60.23.58.9
Chris Dickerson1581.400.23.38.7
Miles Seaborn1530.98.40.23.58.9
Alex Russell1540.16.60.23.48.7
Andrew Presnell15475.30.23.48.6
Patrick Blazek1550.74.10.23.28.3
Kyle Webster1544.75.20.23.38.4
Emerson Keith1546.94.70.23.28.3
Chris Eads1519.990.23.38.3
Zachary Newhouse1514.48.90.23.17.9
Cooper Arnold15237.40.23.17.8
Weston Isaacs1531.95.10.22.97.4
Isaac Heinen15186.10.22.76.9
Coby Guice15008.90.22.76.9
Jake Lauber15263.60.22.56.4
Kevin Jones1544.500.22.46.2
Grady Shue1542.600.22.36.1
Shawn Sullivan1509.55.60.22.46.2
Joshua Anthon1542.200.22.36
Lance Brown1542.100.22.36
Jerome Knott15134.50.22.36
Nick Wood1538.900.22.25.9
Jeff Renner1538.300.22.25.8
Garrett Gurthie153800.22.25.8
Steven Jacobs15006.20.22.35.9
Ziggy Bierekoven1535.400.22.25.7
Benjamin Wiggins15005.90.22.35.8
Jacob Mott1511.33.60.12.25.6
Billy Engel1517.72.50.12.15.6
Noah Meintsma1528.200.125.3
Crispin Carrasco15004.70.12.15.4
Jeffrey Bryk1507.33.20.125.3
Ryan Orton1508.92.70.125.2
Henry Dissell1505.83.10.125.2
Benjamin Callaway1523.800.11.95.1
Ryan Nyc1504.63.20.125.1
Colten Montgomery1530.9-1.60.11.94.9
Robbie Olson1504.62.20.11.94.8
J.C. Kester151500.11.84.7
Bartosz Kowalewski1514.800.11.84.7
Preston Johnson1514.200.11.84.6
Cameron Sheehan151300.11.74.6
Rick Steehler1506.40.90.11.74.6
Thomas Gilbert1511.500.11.74.5
Michael Florey1510.900.11.74.5
Dylan Horst1510.500.11.74.5
Ryan Anderson15070.50.11.74.5
Christian Olsen1502.41.30.11.74.5
Bryan Freese1507.500.11.74.4
Tristan Lucerne1506.900.11.64.3
Kesler Martin1506.800.11.64.3
Russell Jessop1506.700.11.64.3
Peter Bures1503.90.40.11.64.3
Coda Hatfield1505.900.11.64.3
Nate Metzler1505.600.11.64.3
Chris Tellesbo1505.400.11.64.3
Robert Craig1504.400.11.64.2
Brandon Cawthorne1512.8-1.50.11.64.2
Ralf Rogov1503.200.11.64.2
Marshall Blanks1503.200.11.64.2
Tommy Arianoutsos150300.11.64.2
Stephen Schroeder1502.600.11.64.2
Micah Funderburgh1502.100.11.64.1
Cody Taplin1501.900.11.64.1
Richard Little1501.500.11.64.1
Ryan Knuth1502-0.10.11.64.1
Jason Hebenheimer1500.800.11.64.1
Justin Bilodeau1500.700.11.64.1
Dominic Vassari1500.100.11.54.1
Tommy Agent150000.11.54.1
Nathan Allton150000.11.54.1
Jacob Armbrust150000.11.54.1
Jesse Buchanan150000.11.54.1
AJ Carey150000.11.54.1
Linus Carlsson150000.11.54.1
James Chamberlain150000.11.54.1
Curtis Cooper150000.11.54.1
Johan Davidsson150000.11.54.1
Steven Dodge150000.11.54.1
Joe Dirt Douglass150000.11.54.1
Magnus Dunder150000.11.54.1
Jeremy Farnsworth150000.11.54.1
Cody Greenfield150000.11.54.1
Jeremy Harvey150000.11.54.1
Ryan Heeti150000.11.54.1
Tanner Helm150000.11.54.1
James Hufford150000.11.54.1
Tyler Jessop150000.11.54.1
David Johansen150000.11.54.1
Viktor Johansen150000.11.54.1
Ashton Kroenlein150000.11.54.1
Fletch Kuehne150000.11.54.1
Marion Kull150000.11.54.1
Jake Lazzo150000.11.54.1
Lee Letts150000.11.54.1
Zane Letts150000.11.54.1
Joseph Lowe150000.11.54.1
Ricardo Martinez150000.11.54.1
Andrew Marwede150000.11.54.1
Kyle McClure150000.11.54.1
Sam Michaels150000.11.54.1
J.C. Mitchell150000.11.54.1
Jared Neal150000.11.54.1
Cory Obermeyer150000.11.54.1
Brendan Orwig150000.11.54.1
Roderick Plumley150000.11.54.1
Lucas Potts150000.11.54.1
Nichles O. Potts150000.11.54.1
Cody Prugger150000.11.54.1
Chris Richard150000.11.54.1
Nicholas Rowton150000.11.54.1
Kevin Shaffer150000.11.54.1
Brian Shintaku150000.11.54.1
Mario Short150000.11.54.1
George Smith150000.11.54.1
Ben Stafford150000.11.54.1
Justin Starks150000.11.54.1
Henrik Vännström150000.11.54.1
Robin Villman150000.11.54.1
Nick Whited150000.11.54.1
Andrew Wiler150000.11.54.1
Trevor Wilkerson150000.11.54.1
Ryan Wilking150000.11.54.1
Chris Wojciechowski150000.11.54.1
Seth Wood150000.11.54.1
Slim Belcher1499.900.11.54.1
John Jones1499.200.11.54
Alex Berg1499.200.11.54
Alan Wagner1498.700.11.54
Tim Mitchell149800.11.54
Taylor Pennington149800.11.54
Daniel Lindahl1497.400.11.54
Nick Lopez1497.300.11.54
David Potts1497.200.11.54
William Lister1496.600.11.53.9
Tyler Jeffery1496.600.11.53.9
Joseph Bruno1496.500.11.53.9
Zachary Hardham1496.200.11.53.9
Benjamin Smith1495.900.11.53.9
Chris Zagone1495.200.11.53.9
Landen Fledderjohn1494.900.11.53.9
Cory Winant1494.600.11.53.9
Matt Jackson1494.500.11.53.9
Nick Walker1493.800.11.53.8
Jonathan Fletcher1493.300.11.43.8
Brandon Oatman1503.7-2.10.11.43.7
Nicholas Duran1500.3-1.60.11.43.7
Sean Jumbo Slice Roggiero1490.500.11.43.7
Andrew Dominguez1490.200.11.43.7
Thomas Malone1488.700.11.43.6
Brock Shepherd1503.2-2.70.11.33.5
Daniel Sweet1494.6-1.80.11.33.5
Brian Cole1503.8-40.11.23.3
Cory Sharp1494-5.30.112.8
PlayerElo RatingChange In EloWin Prob.Top-5 Prob.Top-10 Prob.
Paige Pierce1708.110.539.899.799.9
Catrina Allen16677.928.598.299.6
Sarah Hokom1618.43.811.282.896.6
Valarie Jenkins1589.33.24.858.490
Jessica Weese1564.22.12.130.876.1
Lisa Fajkus1563.715.11.466.786
Jennifer Allen1559.65.81.636.276.3
Madison Walker15410112.153.7
Zoe Andyke1530.500.78.243.5
Paige Bjerkaas1530.22.60.610.846.6
Melody Waibel1527.90.90.68.342.2
Nicole Bradley1522.400.56.136
Elaine King152200.5635.6
Karina Nowels1518.400.55.232.5
Ellen Widboom1517.200.4531.5
Rebecca Cox1513.80.80.44.829.6
Des Reading1509.87.40.38.433.6
Vanessa Van Dyken1506.200.33.323.1
Nicole Dionisio1503.6-0.30.32.821
Tina Stanaitis1502.7-30.3218.3
Kona Star Panis1501.300.22.719.8
Emily Beach150000.22.519
Andrea Meyers150000.22.519
Missy Gannon150000.22.519
Sarah Gilpin150000.22.519
Erin Griepsma150000.22.519
Christina Linthicum150000.22.519
Colleen Thompson150000.22.519
Angelina Videtto150000.22.519
Sydney Wallenfelsz150000.22.519
Jennifer Wheeling150000.22.519
Nicole Young150000.22.519
Sai Ananda1499.400.22.518.7
Denise Cameron1497.3-2.10.21.816
Kristy Moore1494.700.22.116.1
Marla Tuttle1494.400.2215.9
Kaylee Kincaid1493.3-9.50.20.710
Kelly Tucker1493.100.21.915.3
Lauren Butler1492.700.21.915

  1. I added results from 2012 through 2016 for the Open division and 2016 and 2017 for the Open Women’s division, which currently adds up to 134 events for Open and 20 events for Open Women. This is one of the reasons the values look so different for each division and why, at this point, it would be inappropriate to compare Elo ratings between divisions. 

  2. Note that their Elo ratings are almost identical, which is consistent with their PDGA ratings. Both ratings systems also indicate what is widely known to those who follow the pro game: they have been both the best and most consistent players over the past several years. 

  3. We know that the courses played at the 2017 GBO and 2018 GBO are different and that the 2017 event was shortened due to dangerous weather conditions. This makes this small portion of the model somewhat questionable for this specific event. Nonetheless, the tournament is at roughly the same time of year in the same city/general location and is still at the PDGA NT level with a similar size field. In those respects, not every variable between each year is completely different. Additionally, it is important to include this aspect of the model now—as the model is developed and refined—as high-level events become increasingly standardized. Comparing how this aspect of the model functions for the 2018 GBO compared to how it functions for the 2017 and 2018 Masters Cup, for example, will be illuminating considering the 2018 Masters Cup next month will be played on the same courses, in the same order as they were in 2017. 

  4. A table of probabilities for all players is at the end of the article. 

  5. To estimate win and top 10 probabilities I used a logistic regression, which is a type of statistical model that deals with categorical outcomes (win, no win, or top 10, no top 10). Including how a player played the year before turns out to be important because the model “fits” turn out to be better. Including data from the tournament two years back does not seem to be as informative, perhaps due to significant changes in tournament layouts, player abilities, or diminishing returns due to reduced sample size in the model. 

  6. More specifically, I calculated strength of field as the mean Elo rating for all players in playing the event. 

  7. The cross-validation was based on all tournaments in the dataset. See endnote 1. 

  8. There has been a great deal of parity this year regarding winners in the MPO division. This is very different than in past years and is not reflected in the model. But if this trend continues, the model will adjust accordingly. 

  1. Aaron Howard
    Aaron Howard

    Aaron Howard is a Visiting Assistant Professor at Franklin & Marshall College. He loves to play disc golf and to think about things he loves quantitatively. Contact him at [email protected] and follow him on Instagram.

TAGGED: , , ,

More from Ultiworld
Comments on "Glass Blown Open Preview: Win Probabilities"

Find us on Twitter

Recent Comments

Find us on Facebook