15 is now down to 9, it’s time for the semifinals in this year’s Tournament of Champions. The prediction model has been re-run 100,000 times, and it has come up with the predictions below:
(Note: 1st/2nd/3rd are the model’s predictions for first, second, and third respectively in the final.)
Monday:
Sam Kavanaugh:
Wins SF: 36.899% of the time.
1st: 9.706% of the time.
2nd: 9.722% of the time.
3rd: 17.471% of the time.
Karen Farrell:
Wins SF: 30.553% of the time.
1st: 5.277% of the time.
2nd: 13.087% of the time.
3rd: 12.189% of the time.
Ryan Hemmel:
Wins SF: 32.548% of the time.
1st: 7.169% of the time.
2nd: 10.686% of the time.
3rd: 14.693% of the time.
Andy’s Thoughts: The prediction model has Sam as a very slight favorite; as is usual with him, though, this will come down to whether or not he can find and convert the Daily Doubles (it’s because of the extra variance that the Daily Doubles provide that the prediction model favors Sam or Ryan here; Karen is the strongest of the three players otherwise). If Karen finds success on the Daily Doubles herself, though (and she’s certainly due for that), it’ll be an easy ticket to the final for her.
Tuesday:
Ryan Bilger:
Wins SF: 48.419% of the time.
1st: 24.269% of the time.
2nd: 14.061% of the time.
3rd: 10.089% of the time.
Veronica Vichit-Vadakan:
Wins SF: 31.789% of the time.
1st: 11.443% of the time.
2nd: 11.808% of the time.
3rd: 8.538% of the time.
Kevin Walsh:
Wins SF: 19.792% of the time.
1st: 4.455% of the time.
2nd: 6.806% of the time.
3rd: 8.531% of the time.
Andy’s Thoughts: Ryan and Veronica were probably the two strongest players overall in the quarterfinals; they have now drawn each other on a semifinal. The fireworks will be out in this game, though, with Ryan being the favorite to advance to the finals. I think that Kevin would probably need a fortuitous set of circumstances to qualify for the final.
Wednesday:
Jennifer Quail:
Wins SF: 46.668% of the time.
1st: 22.899% of the time.
2nd: 18.618% of the time.
3rd: 5.151% of the time.
Jason Zuffranieri:
Wins SF: 29.524% of the time.
1st: 9.272% of the time.
2nd: 9.322% of the time.
3rd: 10.930% of the time.
Nibir Sarma:
Wins SF: 23.808% of the time.
1st: 5.510% of the time.
2nd: 5.890% of the time.
3rd: 12.408% of the time.
Andy’s Thoughts: This semifinal has two of the top regular-season winners in Jennifer and Jason; Jennifer’s quarterfinal performance has her as a favorite here. Nibir is strong enough to pull off an upset, though, if he can find and convert Daily Doubles (and if Final is favorable for him).
We have many new offerings at The Jeopardy! Fan Online Store! Proceeds from the sale of the “Doctor Oz’s Fast-Acting Snake Oil Elixir” T-shirt are being donated to The Trevor Project:
Contestant photo credit: jeopardy.com
When commenting, please note that all comments on The Jeopardy! Fan must be in compliance with the Site Comment Policy.
If you are going to quote any information from this page or this website, attribution is required.
So the model essentially installs Ryan B & Jennifer as strong co-favorites to not only to win their semifinals, but be the finals TOC victor in over two thirds of the simulations. Seems very reasonable and likely, but looking forward to see what happens!!
Correction to my math – either Jennifer or Ryan B win almost half (47%) of the time, not two thirds (67%) of the time.
Making predictions is fine, but implying that these predictions have a precision of one part in 1000 is nonsense. Having whole numbers for your odds makes sense, but even a single fractional digit is a stretch. Your predictors simply do not have that strong a relationship with the results.
Spurious precision is described in https://en.wikipedia.org/wiki/False_precision .
Phil:
I think your criticisms are invalid.
I have clearly stated that the model was run 100,000 times and are reporting accordingly.
538 works in a similar fashion with its NCAA projections during March Madness—projecting to the end of the tournament multiple times—and reports similar precision.