RPI vs KenPom

[Jamar Howard 4 President]

A few days ago, WSU's RPI was 8, KenPom was 13.
WSU played a really bad Drake team on the road and squeaked out a win.
Now, RPI is 9, KenPom is 19.

I think KenPom's adjustment was much more accurate.

(Yes, I know this is a very, very small point and I plan on making conclusions later based on bigger picture data. Just thought it was worth sharing to show how KenPom can even see a road win and still not get fooled. It knew WSU performed poorly, while the RPI almost considered the game a wash.)

[Jamar Howard 4 President]

Disappointed I missed including Florida on this list. As of today, RPI has them at 131. KenPom at 22. Will be an interesting case to follow. I'll just have to reference back to 1/8, not 12/29, in their case.

[Kel Varnsen]

I'd like to add a paraphrased quote from Andy Glockner, one of my favorite follows on Twitter..."The goal of sports is to win games. Determining who the best team is isn't necessarily tied to that."

A great illustration of why I prefer KenPom and Sagarin as opposed to RPI, and why the selection committee needs to get rid of RPI.

[ripemupshocks]

Disappointed I missed including Florida on this list. As of today, RPI has them at 131. KenPom at 22. Will be an interesting case to follow. I'll just have to reference back to 1/8, not 12/29, in their case.

According to RPI Live, the current RPI rank for Florida is #95. On 12/29 Florida was ranked #94 in the RPI, and #14 by Kenpom.

[Shock Therapy]

Having watched Florida a few times, I have to say that they're probably about halfway between their RPI Rank and KenPom rank. They aren't great but saying they're as bad as Creighton is a bit of a stretch.

[Jamar Howard 4 President]

According to RPI Live, the current RPI rank for Florida is #95. On 12/29 Florida was ranked #94 in the RPI, and #14 by Kenpom.

Thanks for digging that up. I'll add the 94 and 14 to my original table.

[Cdizzle]

I'd like to add a paraphrased quote from Andy Glockner, one of my favorite follows on Twitter..."The goal of sports is to win games. Determining who the best team is isn't necessarily tied to that."

A great illustration of why I prefer KenPom and Sagarin as opposed to RPI, and why the selection committee needs to get rid of RPI.

I am not sure I understand you completely. Isn't the RPI a better measure purely of whether a team won or lost games, which as you say, is the point? It is unbiased by MoV or other stats (not that these data are bad, but in terms of telling a story of who actually won games, they are pretty pointless). KenPom and Sagarin do a better job of determining who the better teams might be despite game results, and may be better predictive metrics. In other words, doesn't RPI tell us who won games against whom, while metrics like KenPom help us guess which team is actually better?

Which brings me to a good question. At the end of the year, should the selection committee reward a team that KenPom likes, because the metrics show they are a very good team? Or should they reward a team that the RPI likes, which shows how well a team did at accomplishing the predefined goal of actually winning games?

[Jamar Howard 4 President]

I think Kel was trying to say is that the goal in sports is to win, but choosing who is the best team needs to be a separate endeavor because wins/losses don’t tell the whole story. As a player, you simply go out and try to beat the opponent, whoever they might be. As a judge of merit, such as the selection committee, you have a different purpose. Ranking teams is not the same as playing games. Therefore the goals and tools will be different. Wins/losses are the basic goal of the player. More advanced tools are the necessity of the team evaluator.

In regards to your question about what the selection committee should use, I don’t think any of us want to see 26-6 Louisiana Tech make the tournament and get seeded ahead of 26-8 Wichita State. (Just a random example from 2013) That is an extreme example, but it shows that everyone is in agreement that wins/losses shouldn’t be the ONLY means of evaluating who is best. The disagreement isn’t about whether or not to include other factors, it is just about how heavily to lean on those other factors and which other factors to use.

One last thought. The RPI is not a pure “the goal is to win, so the team who wins the most gets ranked the highest”. If we were to try and follow that logic, we would just look at wins and loses directly. Sure, the formula only analyzes wins and losses, and it ignores point spreads, but by taking into account opponents’ wins/losses, it often tells team A that although they won more games than team B, team B is better because of a tougher SOS. The formula is primitive, but the concept of going beyond “the goal is to win” and digging a little deeper is still there, even in the dumb old RPI.

[Cdizzle]

I love KenPom. Use it all the time. But I sincerely hope that the selection committee never utilizes a metric that includes MoV in its calculations. It may be valid, and it may be helpful in being predictive, but to me it creates an objective for teams that should not exist and is counter to the spirit of amateur athletics.

[Jamar Howard 4 President]

I believe KenPom gives margin of victory less and less significance the farther it strays away from 1. So the difference in his formula between a 1 and 10 point win is greater than the difference between a 31 and 40 point win.

I think this takes care of any concerns about teams running up the score or violating "the spirit of amateur athletics". I just feel like one way or the other, a win by 1 must be given less significance than a win by double digits.

[Cdizzle]

KenPom liked the road win at Loyola.

[Jamar Howard 4 President]

	Dec	29		Jan	21
Team	RPI	KenPom		RPI	KenPom
VCU	3	14		4	18
Wichita State	8	13		10	11
Northern Iowa	10	26		24	20
Old Dominion	12	62		29	43
George Washington	17	38		45	63
Colorado State	19	55		37	66
LSU	20	54		41	40
Buffalo	21	82		47	77
Louisville	26	6		32	13
Texas	30	10		16	12
Oklahoma	36	12		25	10
Georgia Tech	38	89		87	94
Wofford	39	88		50	108
Incarnate Word	40	174		148	179
Penn State	41	84		101	122
Eastern Washington	47	104		61	119
High Point	58	148		85	148
Stony Brook	59	150		94	132
Minnesota	62	27		107	53
Gardner Webb	63	167		100	174
Ohio State	65	11		60	22
St. Francis PA	67	143		124	177
Lafayette	68	142		118	172
UConn	80	32		70	47
Syracuse	81	31		58	62
Texas Southern	91	178		116	153
Florida	94	14		75	39
Radford	97	173		187	167
Notre Dame	98	23		39	15
Texas Arlington	99	188		139	187
Indiana	104	44		43	54
Creighton	126	76		151	110
Wyoming	143	56		86	72
McNeese State	144	302		219	264
New Orleans	158	305		252	301
Fairleigh Dickinson	168	294		246	322
Delaware State	170	248		205	254
North Dakota	185	319		268	316
NJIT	197	258		184	208
Southern Illinois	321	202		289	237

4 weeks have passed since my initial post. Even I am surprised just how well KenPom has dominated RPI.

Green = KenPom was better
Red = RPI was better

What I mean by saying KenPom "was better" with a specific team is that KenPom's ranking stayed fairly stable while the RPI ranking moved significantly in KenPom's direction. The reverse would be true for NJIT, the only team on my list where the RPI seems to have had the more accurate ranking 4 weeks ago.

I'll update this again later in the season, but I think we can already see clearly why I always say that KenPom is significantly better than RPI early in the season.

[Jamar Howard 4 President]

Yes, I can already hear the complaints about my analysis of "better". I admit this isn't perfect, but I ask any skeptics to get past the small specifics and look at the bigger picture. There are numerous teams like North Dakota, where RPI changed by nearly 100 spots and KenPom stayed almost exactly the same. There are very few major examples of the opposite happening in the RPI's favor. Sure, we could argue if I should have made Creighton red instead of leaving them neutral. If someone thinks their "true ranking" should be around 150, then yes, RPI has been the better judge of Creighton so far.

My point is simply this. We can argue about any one team, but the sum of the parts gives a clear trend. In general, over the past 4 weeks, RPI rankings have moved toward KenPom much more often than the other way around. KenPom has stayed steady much more consistently than RPI, which has changed significantly in just 4 weeks time. I think this is why we can easily crown KenPom champ.

[wufan]

duplicate post

[wufan]

Yes, I can already hear the complaints about my analysis of "better". I admit this isn't perfect, but I ask any skeptics to get past the small specifics and look at the bigger picture. There are numerous teams like North Dakota, where RPI changed by nearly 100 spots and KenPom stayed almost exactly the same. There are very few major examples of the opposite happening in the RPI's favor. Sure, we could argue if I should have made Creighton red instead of leaving them neutral. If someone thinks their "true ranking" should be around 150, then yes, RPI has been the better judge of Creighton so far.

My point is simply this. We can argue about any one team, but the sum of the parts gives a clear trend. In general, over the past 4 weeks, RPI rankings have moved toward KenPom much more often than the other way around. KenPom has stayed steady much more often too. I think this is why we can easily crown KenPom champ.

But you have Kenpom as being better 20 times and not better 20 times. The sum of the parts says they are the same.