Sagarin says

The standard deviation is about 14 points. So, if +5 is the average expected result you'd expect about 2/3 of the outcomes to be between -9 and +19. +5 implies that the favored team would win approximately 65% of the time.

It's early days for the Sagarin model. As reformedUNDfan points out NDSU has outperformed the current predictions for all its previous games. There are probably a couple of things driving that.

First, the model isn't well connected so its still using preseason weights in its calculation (this will likely be the case until mid October). Presumably these are based on last year's performance but I haven't seen anything definitive about how Sagarin determines his starting values. If this is the only reason (probably not true) that NDSU has outperformed the predictor in every contest so far that would imply that NDSU should receive a boost to its rating as time passes and the model relies less on the starting values and more on this year's results.

Our opponents thus far may simply be playing poorly against us and better in their other games.

Our opponents starting values may be skewed to high which would make the projected margin too small. To the extent that is happening as the model relies less on starting values the quality of our opponents will decline. To the extent that the starting values overestimate the quality of our opponents thus far that will put downward pressure on NDSU's rating as time passes.

Quote:

---

Originally Posted by bisonaudit

The standard deviation is about 14 points. So, if +5 is the average expected result you'd expect about 2/3 of the outcomes to be between -9 and +19. +5 implies that the favored team would win approximately 65% of the time.

It's early days for the Sagarin model. As reformedUNDfan points out NDSU has outperformed the current predictions for all its previous games. There are probably a couple of things driving that.

First, the model isn't well connected so its still using preseason weights in its calculation (this will likely be the case until mid October). Presumably these are based on last year's performance but I haven't seen anything definitive about how Sagarin determines his starting values. If this is the only reason (probably not true) that NDSU has outperformed the predictor in every contest so far that would imply that NDSU should receive a boost to its rating as time passes and the model relies less on the starting values and more on this year's results.

Our opponents thus far may simply be playing poorly against us and better in their other games.

Our opponents starting values may be skewed to high which would make the projected margin too small. To the extent that is happening as the model relies less on starting values the quality of our opponents will decline. To the extent that the starting values overestimate the quality of our opponents thus far that will put downward pressure on NDSU's rating as time passes.

---

another factor in UNIs ranking is the ranking inflation that occurs due to playing a DII opponent. NDSUs SOS and ranking is pulled down due to the poor competition of pvamu and bob Morris. UNIs is not similarly pulled down because the ranking does not take DIIs into account. Their SOS and ranking are inflated as a result. How much, who knows. But it's there.

Quote:

---

Originally Posted by Tatanka

another factor in UNIs ranking is the ranking inflation that occurs due to playing a DII opponent. NDSUs SOS and ranking is pulled down due to the poor competition of pvamu and bob Morris. UNIs is not similarly pulled down because the ranking does not take DIIs into account. Their SOS and ranking are inflated as a result. How much, who knows. But it's there.

---

There may be an effect from this but keep in mind that in addition to NDSU's SOS being pulled down by playing a couple of relatively weak opponents early NDSU is also receiving credit for pounding them. When UNI plays a DII their SOS isn't harmed, true, but they also receive no credit for the win or the margin or victory.

Quote:

---

Originally Posted by Tatanka

another factor in UNIs ranking is the ranking inflation that occurs due to playing a DII opponent. NDSUs SOS and ranking is pulled down due to the poor competition of pvamu and bob Morris. UNIs is not similarly pulled down because the ranking does not take DIIs into account. Their SOS and ranking are inflated as a result. How much, who knows. But it's there.

---

in sagarin, all sub-d1 teams are counted as a single team. The model considers carrol college, south dakota school of mines, etc to be the same team. 'Unrated' has gone 4-46 this year.

Quote:

---

Originally Posted by reformedUNDfan

in sagarin, all sub-d1 teams are counted as a single team. The model considers carrol college, south dakota school of mines, etc to be the same team. 'Unrated' has gone 4-46 this year.

---

I'm not quite sure how this works. There is a line number 247 for unrated w/ a zero SOS and a -90 rating which implies that its part of the model but the introductory comments also state that "ONLY games between the 246 TEAMS RATED here are used for RATING and SCHEDULE STRENGTH computations" (emphasis theirs). It's confusing and until today I was thinking and probably posted earlier in this thread along the same lines what I've quoted from you. But it occurs to me that the 247th unrated line may be there simply to reconcile the W and L columns because the introductory language is quite explicit.

Things are beginning to stabilize, though we are still not well connected. NDSU and Indiana St were the big winners in conference, while Southern Illinois was the big loser. The MVFC continues to dominate with the highest conference ranking and three of the top four individual spots. The Bison are just head and shoulders above everyone else in the FCS. In one respect(points), there is a bigger gap between NDSU and YSU than us and Ohio State(21th). In simple rank, the difference between us and YSU is the same as us and Arizona State(9th). It's not really a valid way of looking at things, but it's still fun.

Sagarin's predictions for week 6:

Code:

---

                              Sagarin          Predict    Result        Diff
 46        North Dakota State        74.59                       
216        Robert Morris                35.47          +41.81    +52.00        +10.19
132        Colorado State                56.83          +15.07    +15.00        - 0.07
239        Prairie View A&M        24.86          +52.42    +59.00        + 6.58
 87        Northern Iowa                65.53          + 6.37    +12.00        + 5.63
 83        Youngstown State        66.60          +10.68               
135        Indiana State                56.68          +20.60               
150        South Dakota                53.26          +21.33               
174        Southern Illinois        48.32          +28.96               
185        Missouri State                45.41          +26.49               
110        South Dakota State        61.15          +16.13               
104        Illinois State                62.06          + 9.84               
                                       
192        Western Illinois        42.41                       
                                       
        Home        2.69

---

Sagarin FCS Predictor Top-10

Code:

---

46  North Dakota State
 83  Youngstown State
 85  Cal Poly
 87  Northern Iowa
 88  Harvard
 90  Georgia Southern
 96  Wofford
100  Eastern Washington
101  James Madison
104  Illinois State

---

Sagarin Predictor Top-4 FCS Conferences

Code:

---

1.  MVFC        57.77
2.  Colonial        55.68
3.  Big Sky        54.14
4.  Southern        53.87

---

This is pure wild-assed speculation, but something cool could happen next year if things go just right. If we win out and Kansas St finishes strong, we will both have high starting positions next year. KSU will almost certainly be in the top-30(maybe top-10), and NDSU should stay around the top-40/50. This is important because there are bonuses for playing(and beating) top-10/-30 teams. If NDSU were to pull out a win at Manhattan, it might be just enough to push NDSU into the top-30. Long shot, but it could be possible. That would have a ripple effect on the rest of the conference's SOS. It would probably be enough to put the MVFC above at least one FBS conference. The effect wouldn't last through the season unless KSU performs really well after that, but it would be cool for awhile.

Sagarin says we are favored by 2 touchdowns over #2 ranked Mt. St.

Dont care about MT ST my only concern is Youngstown.

msum = winless our sagarin cant be that good :(

Quote:

---

Originally Posted by Rockbear99

Dont care about MT ST my only concern is Youngstown.

---

Agree. I wonder if the spread has every been two touchdowns between #1 and #2.

Quote:

---

Originally Posted by Rockbear99

Dont care about MT ST my only concern is Youngstown.

---

Yup...this old playoff rival will bring it. Our defense simply must answer.

Using Sagarin's Predictor rankings, NDSU (74.59) is currently ahead of the MAC-leading Ohio Bobcats (69.07). Not too shabby. It'll be fun to check again when the teams are well connected.

Quote:

---

Originally Posted by riceweb

It'll be fun to check again when the teams are well connected.

---

I knew a few girls in college who were, ahem, "well connected" to the team. I never knew whole teams did the same thing.

http://usatoday30.usatoday.com/sports/sagarin/fbt12.htm

this says NDSU at 50..........where are you all seeing 46?? I know I know I should just claim stuff and not use a link, but it aint my style

Quote:

---

Originally Posted by SamsRams

http://usatoday30.usatoday.com/sports/sagarin/fbt12.htm

this says NDSU at 50..........where are you all seeing 46?? I know I know I should just claim stuff and not use a link, but it aint my style

---

Those were Sept 29th rankings

Today is Oct. 1st





:)

Quote:

---

Originally Posted by SamsRams

http://usatoday30.usatoday.com/sports/sagarin/fbt12.htm

this says NDSU at 50..........where are you all seeing 46?? I know I know I should just claim stuff and not use a link, but it aint my style

---

ndsu is 46 in the predictor column...

I can't imagine where'd we be ranked if our SOS was half of what it is now.

Quote:

---

Originally Posted by SamsRams

http://usatoday30.usatoday.com/sports/sagarin/fbt12.htm

this says NDSU at 50..........where are you all seeing 46?? I know I know I should just claim stuff and not use a link, but it aint my style

---

I was wondering how long it would take for this question to come up this year. Took longer than I expected.

Look at the ratings on the USA Today link. You'll see this for NDSU:

Code:

---

                              RATING    W  L  SCHEDL(RANK) VS top 10 | VS top 30 | ELO_CHESS    | PREDICTOR 
 50  North Dakota State  AA =  74.31    4  0  46.11( 209)    0  0  |    0  0  |  71.79  59 |  74.59  46

---

Notice the columns labeled RATING, ELO_CHESS and PREDICTOR. Sagarin(the guy) likes the PREDICTOR rating. It includes margin of victory and is the best predictor of future games(hence the name). The BCS wanted to use Sagarin's ratings, but didn't like that margin of victory was included. In order for Sagarin's numbers to be used for the BCS calculation, he had to strip margin out of the computation. That resulted in the ELO_CHESS version which only looks at wins and losses. For some reason, either Sagarin or USA Today decided to create a third computation which sort of splits the difference. That became the RATING number.

The main list is arranged using the RATING computation. Personally, I prefer the PREDICTOR column because Sagarin himself says it's the most accurate. It takes a little more work to redo the top-10 FCS teams and top-4 FCS conferences as PREDICTOR rankings, but I think it's worth the time. Either I've convinced enough other posters to switch to my side or they're just sick and tired of this explanation. Either way, most of BV seems to use the PREDICTOR column now. Of course NDSU seems to always rank a little higher in the PREDICTOR ranking, so that might also be the reason. ;)

Quote:

---

Originally Posted by bisonnation11

I can't imagine where'd we be ranked if our SOS was half of what it is now.

---

Teams that player dii or naia schools are enjoying some big time SOS inflation. As it stands for ndsu, pvamu is going to be an anchor in that ranking all year long. But hey at least they ain't valpo.

Quote:

---

Originally Posted by Tatanka

Teams that player dii or naia schools are enjoying some big time SOS inflation. As it stands for ndsu, pvamu is going to be an anchor in that ranking all year long. But hey at least they ain't valpo.

---

Our SOS ranking should end somewhere around 170, give or take 15 spots.

I like Saragin, but I can do better. If we don't lose any games this year we are holding another Natty troph!! How's that!?


Sent from my iPhone using Tapatalk

Quote:

---

Originally Posted by CAS4127

I like Saragin, but I can do better. If we don't lose any games this year we are holding another Natty troph!! How's that!?


Sent from my iPhone using Tapatalk

---

If you really can do better then you COULD be a very wealthy man in short order.

Sent from my DROID RAZR using Tapatalk 2

I am wealthy!! I just finished eating a piece of apple pie given to me by a "former" UND fan from BisMan who watched our game with us last weekend at the Stadium, my little girl is sleeping after a fun nite together, I get to send her off to school tomorrow, and then do it over again tomorrow nite. Wait ... R you talking $$$?! Life is not so bad--plus I get to enjoy Bison FB on Saturday with friends, family and my fellow tailgaters. Not sure what else a man needs in life!! I already have guns, and Lakes is a Facebook friend--just sayin'!!


Sent from my iPhone using Tapatalk

Quote:

---

Originally Posted by Hammersmith

This is pure wild-assed speculation, but something cool could happen next year if things go just right. If we win out and Kansas St finishes strong, we will both have high starting positions next year. KSU will almost certainly be in the top-30(maybe top-10), and NDSU should stay around the top-40/50. This is important because there are bonuses for playing(and beating) top-10/-30 teams. If NDSU were to pull out a win at Manhattan, it might be just enough to push NDSU into the top-30. Long shot, but it could be possible. That would have a ripple effect on the rest of the conference's SOS. It would probably be enough to put the MVFC above at least one FBS conference. The effect wouldn't last through the season unless KSU performs really well after that, but it would be cool for awhile.

---

ndsu got up to 18th in 2007 iirc.

thank you hammersmith

Quote:

---

Originally Posted by Tatanka

Teams that player dii or naia schools are enjoying some big time SOS inflation. As it stands for ndsu, pvamu is going to be an anchor in that ranking all year long. But hey at least they ain't valpo.

---

True, if you only look at SOS in isolation. But in the rankings they are also getting no credit for how they performed in that game.

Quote:

---

Originally Posted by bisonaudit

True, if you only look at SOS in isolation. But in the rankings they are also getting no credit for how they performed in that game.

---

true, but does SoS factor into the ranking? I'll bet it does. Ndsus ranking is getting pulled down by pvamus horrendous ranking. No matter how well teams playing lower division teams do, they're not experiencing a similar effect. A perfect example is UNI. They are ranked highly despite being 0-4 (central state doesn't count). PVAMU is also winless. What's the difference in their ranking? SoS.

Sagarin’s strength of schedule is implicit in his rankings, as each rating compounds both records of opponents and records of opponents’ opponents. teams playing lower opponents get a free pass while teams playing poor division I teams get penalized (and rightly so).

Quote:

---

Originally Posted by Tatanka

true, but does SoS factor into the ranking? I'll bet it does. Ndsus ranking is getting pulled down by pvamus horrendous ranking. No matter how well teams playing lower division teams do, they're not experiencing a similar effect. A perfect example is UNI. They are ranked highly despite being 0-4 (central state doesn't count). PVAMU is also winless. What's the difference in their ranking? SoS.

Sagarin’s strength of schedule is implicit in his rankings, as each rating compounds both records of opponents and records of opponents’ opponents. teams playing lower opponents get a free pass while teams playing poor division I teams get penalized (and rightly so).

---

SOS factors into the ratings, but I wouldn't necessarily say that NDSU's ranking is getting pulled down by Prairie View's poor SOS. The model predicts NDSU should have won by 52. NDSU won by 59. Outperforming the projection, all else equal, increases your rating. If Central State would have been in the Sagarin model, UNI's 59 point win may not have been more than the expected margin and their rating may have been harmed as a result, or as with NDSU and Prairie View, it may have been a marginal benefit. UNI likely remains highly rated for a couple of reasons. This is off the cuff w/out a deep dive into the numbers. One, they had a strong start value which will remain in the model until for another couple of weeks. Two, they lost two close games to D-IA teams on the road. Margin matters. If you lose close to a superior team it's entirely possible that your rating will increase. If you win close against an inferior team it's entirely possible that your rating will decrease. People punish UNI more severely for losing close to better teams than the computer does.

So looking at UNI's numbers in a way similar to how Hammersmith presents NDSU's Sagarin data each week shows that they played Wisconsin 10 points better than the model predicts, 1 point poorer against Iowa, 3 points poorer against YSU, and 6 points poorer against NDSU. The net is zero. Which I'd interpret as saying that the starting value Sagarin assigned them is quite close to their current rating of 65.53, though there could be other things going in with how the algorithm fits it's prediction to the actual results thus far.

As Dennis Green would say "They are who we thought the were." Sagarin's algorithm isn't "surprised" that UNI is 0-4 so it hasn't moved them off of their starting position very much. They were at 77th and 68.36 in the predict column before they played Iowa and they're at 87th and 65.53 now.

Quote:

---

Originally Posted by Tatanka

A perfect example is UNI. They are ranked highly despite being 0-4 (central state doesn't count).

---

Just had to mention that I beleive UNI is a talanted team, despite their unlikable coach, and probably among the 10 best in the FCS. Please don't neg rep me for saying that cause it does hurt a little to say it.:)

Quote:

---

Originally Posted by perthbison

Just had to mention that I beleive UNI is a talanted team, despite their unlikable coach, and probably among the 10 best in the FCS. Please don't neg rep me for saying that cause it does hurt a little to say it.:)

---

hard to disagree with that. Having said that, I smile a little more each day knowing they are 1-4 with 0 division I wins.

Quote:

---

Originally Posted by perthbison

Just had to mention that I beleive UNI is a talanted team, despite their unlikable coach, and probably among the 10 best in the FCS. Please don't neg rep me for saying that cause it does hurt a little to say it.:)

---

It shouldn't hurt. If true, it should feel good because we had a 19 point 4th quarter lead on said team before giving up a garbage touchdown.

Sagarin projects NDSU to defeat YSU 72.3% (Note: this includes an adjustment for YSU coming off a bye week equal to the home field advantage. 78.5% if you don't believe in the bye week thing.)

Regular season record projection based on Sagarin's ratings:
11-0 36.8%
10-1 42.1%
9-2 17.5%
8-3 3.3%
7-4 0.3%
6-5 0.01%
5-6 0.0003%
4-7 0.000002%

Quote:

---

Originally Posted by bisonaudit

Sagarin projects NDSU to defeat YSU 72.3% (Note: this includes an adjustment for YSU coming off a bye week equal to the home field advantage. 78.5% if you don't believe in the bye week thing.)

Regular season record projection based on Sagarin's ratings:
11-0 36.8%
10-1 42.1%
9-2 17.5%
8-3 3.3%
7-4 0.3%
6-5 0.01%
5-6 0.0003%
4-7 0.000002%

---

No doubt, there are a lot of smart people on this board......you should edit this each week.....pretty cool stuff.

Quote:

---

Originally Posted by THEsocalledfan

No doubt, there are a lot of smart people on this board......you should edit this each week.....pretty cool stuff.

---

He did last year. I love this sort of analysis.

If we beat YSU the percentage for 11-0 will jump quite a bit.

Quote:

---

Originally Posted by bisonaudit

Sagarin projects NDSU to defeat YSU 72.3% (Note: this includes an adjustment for YSU coming off a bye week equal to the home field advantage. 78.5% if you don't believe in the bye week thing.)

Regular season record projection based on Sagarin's ratings:
11-0 36.8%
10-1 42.1%
9-2 17.5%
8-3 3.3%
7-4 0.3%
6-5 0.01%
5-6 0.0003%
4-7 0.000002%

---

We don't need guesses. We need more TD's and less injuries. I bet those YSU boys can't sleep right now.. like me!

Sagarin rankings are now WELL CONNECTED, and Sagarin says #37! And #33 in the Predictor ranking! Amazing how 6-0 Ohio is ranked 69th...

Should be a good year for computer rankings.

holy schnikes #37!!!! GO BISON!!!

Well, a bunch of jumping around now that things are well-connected, and not much of it great for the MVFC. Obviously NDSU stays head, shoulders, knees and toes over the rest of the FCS, and UNI(#6) manages to stay in the top-10 with their tough schedule, but YSU(#11) drops just out after their piss-pounding. Laughingly, it appears the Bison under-performed at Colorado State and over-performed just a bit on Sat. With the lousy way some of the Valley performed this weekend, our conference lead over the Colonial has almost evaporated. The top of the Big Sky looks good with three teams in the top-10, but the rest of the conference lets them down and puts them as the weakest of the big four. As for the rest of the schedule, it looks like three TD wins at least on paper from here on out, with Illinois State being the only exception to close the season. Wild.

Sagarin's predictions for week 7:

Code:

---

                              Sagarin          Predict    Result        Diff
 33        North Dakota State        78.51                       
224        Robert Morris                32.58    +48.44    +52.00    + 3.56
146        Colorado State                54.11          +21.89    +15.00        - 6.89
235        Prairie View A&M        29.73          +51.29    +59.00        + 7.71
 90        Northern Iowa                64.47          +11.53    +12.00        + 0.47
109        Youngstown State        61.21          +19.81    +41.00        +21.19
128        Indiana State                57.18          +23.84               
168        South Dakota                49.65          +28.86               
149        Southern Illinois        53.33          +27.69               
187        Missouri State                44.90          +31.10               
118        South Dakota State        59.41          +21.61               
126        Illinois State                57.56          +18.44               
                                       
189        Western Illinois        44.37                       
                                       
        Home        2.51

---

Sagarin FCS Predictor Top-10

Code:

---

33  North Dakota State
 78  Eastern Washington
 81  Georgia Southern
 83  Harvard
 89  Cal Poly
 90  Northern Iowa
 93  Wofford
 95  James Madison
 98  Old Dominion
105  Montana

---

Sagarin Predictor Top-4 FCS Conferences

Code:

---

1.  MVFC        56.63
2.  Colonial        56.32
3.  Southern        55.17
4.  Big Sky        54.11

---