With just 6 games left in the regular season, UND’s PWR outlook remains pretty clear. Consistent with last week’s forecast (that UND could lose two more and likely be in the top 13 at the end of the regular season) and results (one loss), this week’s forecast shows that UND can only lose one more and still be more likely than not to finish the regular season top 13.

However, as also revealed last week, if UND loses two more, the Sioux are right on the cusp (a 47% chance of being #14 or higher) such that a good result and/or a little bit of luck in the WCHA tournament could be enough to push the Sioux into the NCAAs.

Presented a little differently, here are UND chances of being at or above each rank at the end of the regular season based on the number of remaining games the Sioux win:

PWR Rank |
Win 2 | Win 3 | Win 4 | Win 5 | Win 6 |
---|---|---|---|---|---|

1 | 0.00% | 0.00% | 0.00% | 0.00% | 0.01% |

2 | 0.00% | 0.00% | 0.00% | 0.00% | 0.10% |

3 | 0.00% | 0.00% | 0.00% | 0.00% | 1.10% |

4 | 0.00% | 0.00% | 0.00% | 0.02% | 6.72% |

5 | 0.00% | 0.00% | 0.00% | 0.23% | 23.02% |

6 | 0.00% | 0.00% | 0.00% | 1.56% | 51.30% |

7 | 0.00% | 0.00% | 0.01% | 6.03% | 78.00% |

8 | 0.00% | 0.00% | 0.06% | 16.51% | 93.08% |

9 | 0.00% | 0.00% | 0.33% | 33.75% | 98.37% |

10 | 0.00% | 0.00% | 1.35% | 55.06% | 99.73% |

11 | 0.00% | 0.00% | 4.48% | 75.34% | 99.96% |

12 | 0.00% | 0.02% | 12.21% | 89.36% | 100.00% |

13 | 0.00% | 0.18% | 26.55% | 96.59% | 100.00% |

14 | 0.00% | 1.02% | 46.97% | 99.20% | 100.00% |

15 | 0.02% | 4.25% | 68.87% | 99.87% | 100.00% |

16 | 0.16% | 12.70% | 85.82% | 99.99% | 100.00% |

17 | 0.93% | 28.49% | 95.32% | 100.00% | 100.00% |

18 | 3.73% | 49.73% | 98.93% | 100.00% | 100.00% |

19 | 11.86% | 71.49% | 99.83% | 100.00% | 100.00% |

20 | 28.10% | 88.11% | 99.98% | 100.00% | 100.00% |

Remember that once the regular season is finished, UND still has a chance to play up to about five more games in the conference tournament.

## End of regular season outlooks for other WCHA teams on the bubble

Colorado College is in a slightly worse spot than the Sioux. Losing just one more gives the Tigers a 71% chance of finishing #13 or higher, while losing 2 more leaves CC with only a 3% chance of finishing #13 or higher.

Minnesota, in contrast, is in a slightly better spot than the Sioux. Even with two more losses, the Gophers stand a 79% chance of being top 13 at the end of the regular season. With three more losses that plummets to 6.8%, while with only a single loss that rockets to 99.2%.

## One week outlook

The Sioux, once again, face a large spread in their possible PWR outcomes for the weekend. A sweep is most likely to push the Sioux into the 20-22 range, while getting swept is likely to drop them as much as ten spots.

Ferris St., sitting on its first #1 PWR ranking, is going to have to work this weekend to hold onto it. Even with a sweep, the Bulldogs have only a 35% chance of staying #1, while with a split that likelihood drops to 9%. The series, other than their own, which would be most beneficial to Ferris St this week is Merrimack defeating Boston College.

Minnesota faces an even bigger spread than UND. The Gophers have big stakes in quite a few games this week, cheering for (in order of importance):

- Wisconsin over Denver
- St. Cloud over Alaska Anchorage
- Boston College over Merrimack
- Massachusetts over Maine

Finally, Colorado College is the only one of the three WCHA bubble teams that is unlikely to move into tournament position this weekend, even with a sweep.

## Methodology

Each forecast is based on at least a million monte carlo style simulation of the remaining games in the regular season. For each simulation, the PairWise Ranking (PWR) is calculated and the results tallied. The probabilities presented in the forecasts are the share of simulations in which a particular outcome occurred.

The outcome of each game in each simulation is determined by random draw, with the probability of victory for each team set by their relative KRACH ratings. So, if the simulation set included a contest between team A with KRACH 300 and team B with KRACH 100, team A will win the game in very close to 75% of the simulations.

## Resources

- Current PWR Rankings (SiouxSports.com)
- CHN PWR Rankings (CollegeHockeyNews.com)
- TBRW build your own rankings (slack.net)
- Explanation of how PWR mimics NCAA tournament selection (CollegeHockeyNews.com)
- A first look at the PairWise Rankings and UND’s tournament possibilities
- Change to COP calculation in PWR formula (USCHO.com)

I love the work you do for these Jim. What series are important for UND this week? Maybe I missed that in the blog post, but I always like to know what other games are important to catch them on tv.

You’re right, I got so distracted by the new table format for the UND forecast that I forgot to include the “games to watch” (even though I did for a few other teams!) I’ll get those up here tomorrow.

Ok, I’m trying a new approach. I’m splitting out which games matter if the Sioux sweep (which we need to climb) vs. those that matter if the Sioux are swept (which we need defensively not to fall).

Here are all the series (in order of impact) that on average move UND at least .75 of a PWR ranking position.

If Sioux sweep:

UW over Denver (sweep)

B.C. over Merrimack (sweep)

Notre Dame over Miami (at least one)

Alaska over Mich. St (at least one)

Mass over Maine (sweep)

Michigan over N. Michigan (sweep)

Quinnipiac over Union

If Sioux split:

Western Mich over Miami (just one)

If Sioux get swept:

Minnesota over Bemidji St (at least one)

Finally, I should note that these are just the outcomes that optimize UND’s PWR this weekend. Our long run interests may well, and often do, lie elsewhere.

Why is the StC victories over AA important to the gophs?

Am I reading this correctly?

One week outlook

The Sioux, once again, face a large spread in their possible PWR outcomes for the weekend. A sweep is most likely to push the Sioux into the 20-22 range, while getting swept is likely to drop them as much as ten spots.

Should it be10 to 12 instead of 20-22? You always do a fantastic job with this – keep it up!

Sorry, you’re right, the graph and table are right, the wording is backwards. From UND’s perspective, it’s getting swept that pushes them into the 20-22 range, while sweeping results in up to 10 spots higher than that.

St. Cloud being a “Team Under Consideration” (TUC) helps the Gophers because Minnesota has a 3-1 record vs. St. Cloud. SCSU’s RPI (.5023 as of Saturday) is low enough that another loss to AA could drop them out of being a TUC, lowering Minnesota’s win percentage vs. TUCs.