Who's panicking?

[FargoBison]

Re: Who's panicking?

I don't put a lot of stock in Sagarin, I'm all about RPI. As for RPI Oakland, ORU and SUU is factored into every team's RPI, I'm not sure if you can just pull them out and say that is accurate.

That said nothing changes the fact that every school but SDSU has either support or facility issues and multiple schools are majorly deficient in both areas. Honestly these schools haven't done a good job in changing that outside of NDSU and USD who have plans to build new/renovate facilities.

[zooropa]

Re: Who's panicking?

I don't put a lot of stock in Sagarin, I'm all about RPI

1-RPI is garbage. And if you assume six games against teams that have an average RPI equal to the average RPI of Oakland, ORU and SUU, you can replace that RPI.

2-The reason for using Sagarin is clearly stated in the post: Sagarin assigns greater weight to middle teams in a conference when ranking conferences.

The middle two teams are 5x as important in determining the Sagarin conference rating than the top or bottom two teams.

The 6 spot improvement shown by the Summit reflects a broad improvement, not two schools doing really super.

3-The Summit outdrew 16 other conferences for its tournament--including conferences like the Horizon and Big Sky that have home games during the tournament. Don't dump on the Summit because it's not the MVC, the MWC or the A-10; the mid-majors are *full* of small and half-empty arenas on commuter campuses.

[FargoBison]

Re: Who's panicking?

I don't like sagarin, I only ever follow RPI and Kenpom. What does the conference tournament attendance have to do with anything I said? The attendance is basically SDSU fans.

I think a rising tide is lifting all boats in the Summit but if you knock ORU and Oakland that might go in the opposite direction. That is my opinion.

If the Summit is going to truly improve...IPFW, IUPUI, UMKC and UNO have to get their acts together in terms of supporting their programs and improving facilities.

[zooropa]

Re: Who's panicking?

I don't like sagarin, I only ever follow RPI and Kenpom. What does the conference tournament attendance have to do with anything I said? The attendance is basically SDSU fans.

I think a rising tide is lifting all boats in the Summit but if you knock ORU and Oakland that might go in the opposite direction. That is my opinion.

Do you know what a WEIGHTED MEAN is?

[RabbitObsessed]

Re: Who's panicking?

I think i'm too drunk for this thread. Good work by both sides. Everyone read zoo's posts with this in mind: he said that Baylor "certainly" wasn't an elite 8 team. Just remember that. It makes them much more fun to read

[FargoBison]

Re: Who's panicking?

Do you know what a WEIGHTED MEAN is?

I know you like Sagarin and I understand you are using it to make a point. But if I don't think the rating system you are using is significant what is the point? Honestly I completely ignored everything you said about Sagarin.

I don't need a rating system to tell me that a number of Summit schools face real issues and these issues are major hindrances as to why they aren't consistently successful. If you toss ORU and Oakland out, every school but SDSU has some significant problems.

[zooropa]

Re: Who's panicking?

he said that Baylor "certainly" wasn't an elite 8 team

They're not.

It's not *my* fault that Duke couldn't beat Lehigh and Xavier didn't pay attention to the SDSU game film and let the Bears posts kill them in iso.

[zooropa]

Re: Who's panicking?

I know you like Sagarin and I understand you are using it to make a point. But if I don't think the rating system you are using is significant what is the point? Honestly I completely ignored everything you said about Sagarin.

Sagarin weights conferences with ten teams this way:

First place = 1
Second place = 2
Third place = 3
Fourth place = 4
Fifth place = 5
Sixth place = 5
Seventh place = 4
Eighth place = 3
Ninth place = 2
Tenth place = 1

Applied to the RPI, the numbers would be:

.5809 * 1
.5776 * 2
.5140 * 3
.5098 * 4
.4893 * 5
.4721 * 5
.4644 * 4
.4413 * 3
.4321 * 2
.4213 * 1

This gives you a total of: 14.59. Now divide that total by 30 (=1+2+3+4+5+5+4+3+2+1) to get the weighted mean conference RPI.*

For the Summit, in 2011/12, that's .4864.

Now the mean RPI for the Summit in 2011/12 is .4903.

The weighted mean is lower than the mean, because it assigns greater weight to teams in the middle of the conference.

The weighted mean for the Summit in RPI in 2009/10 was .4728

That's a significant improvement in weighted mean RPI from '10 to '12.

The improvement, as registered by Sagarin, was enough to bump the Summit from #24 to #18.

I'm not going to provide a comparable assessment in terms of RPI because I'd have to do weighted means for every conference for both years, and it's just not worth it.

*By contrast, the mean would typically be calculated thus:

.5809 * 1
.5776 * 1
.5140 * 1
.5098 * 1
.4893 * 1
.4721 * 1
.4644 * 1
.4413 * 1
.4321 * 1
.4213 * 1

Total is 4.903, divided by 10 is .4903.

[zooropa]

Re: Who's panicking?

Using weighted means on other conferences of note:

2009/10 Big Sky: .4774
2011/12 Big Sky: .4573

2009/10 Sun Belt: .4718
2011/12 Sun Belt: .4618

[witness]

Re: Who's panicking?

Now why exactly is everybody panicking????

[Nidaros]

Re: Who's panicking?

Now why exactly is everybody panicking????

I am enjoying my Sunday Morning coffee and about to turn on Meet the Press.

[SturgisJeff]

Re: Who's panicking?

ahhhh March Madness,it's on the SDSU fans site, the NCAA tournament has nothing on this thread, just like the Nagy thread some others involving AJ, Nate. no one has said a word about leaving, staying, standing on their heads or whatever,from my impressions on talking to the AD at Oakland they are perfectly happy right where they are.

[Prairiehaas]

Re: Who's panicking?

Interesting statistical analysis by Zoo. One question that I don't see answered in the analysis, is the deifference statistically significant? That is when comparing school or conference rankings is the difference greater than the error of measurement?

[zooropa]

Re: Who's panicking?

Interesting statistical analysis by Zoo. One question that I don't see answered in the analysis, is the deifference statistically significant? That is when comparing school or conference rankings is the difference greater than the error of measurement?

Yes, it's statistically significant. See conference ratings here, from RPIRatings.com:
http://rpiratings.com/mensrpi.php

  13. Ivy League          115 117  .4945  14  .4956
  14. Colonial            196 198  .4974  13  .4954
  15. Horizon             151 158  .4924  15  .4941
  16. Summit              147 151  .4819  18  .4859
  17. Metro Atlantic      156 168  .4856  16  .4855

Note that barely more than .001 separates 13th from 17th on this rank (note also that these RPI figures are slightly different than the RealtimeRPI.com figures I used on the other page).

[Prairiehaas]

Re: Who's panicking?

Actually not. Standard error of the mean is not given. A quick calculation for the Summit League teams results in a standard error of 0.0175. Given that a 95% confidence interval about the mean would then be about +/-0.035. So the 95% mean confidence interval for the Summit RPI is 0.517 to 0.447. A quick look at conference RPIs and one can conclude no statistically significant difference in mean RPI between the Summit League and the WAC at No. 123 and the Big South at No. 27.


Hence the problem with using RPI for comparisons of conferences or for that matter teams.