NFL Week 8 Elimination Pool Pick

Ok, the model says to go with the Chiefs at home against the Bills this week. However, I am personally not going to listen to my model this week and I'm going with the Jets instead. My model was going to save the Jets for week 17. But with the best teams resting players in week 17, I don't think it's worth saving one of the few best teams till then. Also, the Jets are coming off a bye week and the best teams tend to win coming off bye weeks. The winless Bills are really due for a win following their OT loss to the Ravens last week. So, in summary, my week 8 pick is the Jets.

NFL Elimination Pool - Week 7 Pick

6 Weeks down and 11 to go! As a reminder, I have already used (team's ESPN power ranking shown in parantheses):

Week 1 - Bears (12)
Week 2 - Packers (15)
Week 3 - Patriots (3)
Week 4 - Falcons (7)
Week 5 - Colts (5)
Week 6 - Steelers (1)

So I still have some good team's left (Notably Jets, Ravens, and Saints). This week there are two potential blowouts on the schedule for me to choose from: Bills at Ravens is the worst team playing the 4th best team and Browns and Saints is the 3rd worst at the 6th best team. The Saints I want to save for week 11 when they have the largest projected blowout on the calendar of the teams I still have available. So, I'm going with the Ravens this week as this is their easiest game left on the 2010 schedule and no other future weeks when they would present the best choice as well.

NFL Elimination Pool - Week 6 Pick

Week 6 is an easy decision for my model. We're going with the Steelers (ESPN's #1 power ranked team) is facing the lowly Browns at home. The only other option I'd even consider is the Giants to defeat the Lions at home. However, the spread between the Steelers and Browns is wider by 15 ranks. By the way, if I still had the Bears available, I would use them over the Giants (but not over the Steelers).

2010 NFL Elimination Pool - Week 5 pick

4 correct picks down, only 13 to go! In week 5 I'm going with the Colts to defeat the undefeated Chiefs this week. The Colts have the largest projected margin of victory of all favorites across all Las Vegas lines this week. I also considered the Ravens to defeat the Broncos at home this week, but I want to save the Ravens for week 7 when they have the Bills at home, and the Bills are even worse than the Broncos. Plus, as I mentioned earlier, according to the Vegas moneylines, the Colts are more likely to win than the Ravens this week.

NFL Survivor/Elimination Pool - Week 4 Pick

Week 4 has a few projected blowouts on the schedule: Panthers @ Saints, Lions @ Packers, and to a slightly lesser degree 49ers @ Falcons. I've already used the Packers, so that leaves me with the Saints or Falcons. According to me, this is the Falcons easiest game until week 17 when they get the Panthers at home. But, as I've discussed before, I downweight future weeks, (b/c your pool might not last until week 17), so you can say this is the best time to use the Falcons (if you're ever going to use them).

The Saints on the other hand, have projected blowouts at home in weeks 7, 11, 14, and 17 versus the Browns, Seahawks, Rams, and Bucs respectively. My model is telling me to save the Saints for week 14 against the Rams because that is the only projected blowout on the schedule that week.

So, my model is saying to go for the Falcons in week 4, and that's what I'm going to do (here's hoping for an 0-4 49ers team). If you have very few people in your pool, and are fairly certain that it will not last until week 14, then go for the Saints.

Also, if you had rebuys in weeks 1 and/or 2 and used bad teams as winners (and still have the packers and bears available), then that changes everything as well...

NFL Survivior Pool - Week 3 Pick

Lots of projected blowouts on the calendar in week 3 including Bills @ Patriots, Browns @ Ravens, and Lions @ Vikings. My model is telling me to go with the Patriots, saving the ravens for week 12 at home against the Bucs, and currently planning to never use the 0-2 Vikings.

NFL Survivor Pool - Week 2 Pick

Looking at the week 2 schedule, Green Bay is the obvious choice, hosting the lowly bills at home. This is one of 2 extremely lopsided matchups for Green Bay this year, they also get to host Detroit in week 4. However, since there aren't any other matchups anywhere near as lopsided this week, this is the ideal time to use Green Bay and there is no need to save them for week 4 (as the Panthers have to visit the Saints in New Orleans in week 4).

2010 NFL Survivor/Elimation/Suicide Pool - Week 1

Welcome back for another exciting start to the NFL season. And with that everyone is alive in their elimination / survivor / suicide pools. Let's cut right to the chase with a week 1 pick. I loaded ESPN's preseason power rankings into my season optimizer to see what it recommended for week 1. It's telling me to pick the Bears for 2 very good reasons. #1 The bears are at home and playing their easiest opponent of the entire season. #2 This game has the widest power ranking disparity of any game on the schedule in week 1 (after giving the home teams a boost for home field advantage). Any questions?

P.S. Is anyone else out there in a pool where you have to pick a different losing team each week? I am, and have a model for that as well...
P.P.S. Is anyone out there in a week with 2 or 3 strikes allowed? In some cases, that can change who you should pick! let me know...

MIT Sloan Sports Analytics Conference

Well, fantasy basketball season is over, so I guess this isn't too relevant. But nonetheless, I have not posted in a while and that's because I've been doing fantasy research. A friend of mine, Paul Raff, and I entered this year's research paper contest at MIT Sloan's Sports Analytics Contest. We were extremely excited when our paper was selected as one of 4 finalists in the contest and we were invited to present the paper at the conference. Below is the abstract of the paper and you can find a link for the paper in its entirety here. Presenting at and attending the conference were great experiences and I am already looking forward to next year's conference and thinking about a new entry for the 2nd annual research paper contest.

In head-to-head fantasy sports leagues, it is common belief that managers try to do their best in all statistics categories. In this paper, we work to turn this notion on its head and investigate the strategy of effectively forfeiting certain categories while focusing on a certain subset of all categories. Through millions of draft and match-up simulations based on 2008-2009 NBA statistics, we found that approximately one-quarter of all possible subsets yielded strategies that defeated the "all statistics" strategy in a head-to-head match-up, and that the "all statistics" strategy is not the overall best one.

PVORP - Projected Value Over Replacement Player

Question: Who is a better to have as the 1st player on your fantasy team: catcher "AA" who will produce 80 runs, 80 rbi, and 15 SBs or CF "BB" who will produce 90 runs, 90 rbis, and 25 SBs?

Answer: AA who has less overall value, is the more valuable fantasy player, b/c he plays catcher. Catcher's don't produce much offense compared to outfielders. If you choose AA, you're still going to have to add a CF... and if you choose BB, you're still going to need a catcher. The point here is that AA + a CF you might add later will likely have more combined value than BB + a different catcher that you might add later.

So the lesson here is that you're evaluating players, don't compare them with each other, compare them with a who else is available at that position. Here is an example of the production you can expect to get from the 12th best player at each of the following positions in runs, RBIs, and stolen bases:

Position	R	RBI	SB
C	50	58	1
1B	84	94	4
2B	78	67	12
3B	77	77	6
SS	76	64	14
LF	79	77	15
CF	80	72	23
RF	80	83	13

AS you can see catcher AA described above is 30, 22, and 14 runs, rbis, and SBs above "replacement" level and CF BB is 10, 18, and 3 runs, rbis, and SBs repectively above replacement level. 30, 22, and 14 are all higher than 10, 18, and 3, so that is why AA is better than BB

Real life example: One of my fantasy leagues, (my family leagues) has keeper rules where you can pick any 2 players from your team the previous year to be assigned to your team this year in the last 2 rounds of the draft. I chose to keep Joe Mauer instead of A-Rod! Yes, A-Rod has more overall production, but the goal is to get the most production across every roster spot. And I think I can do better at C & 3B by starting that duo off with Mauer and adding a 3B later than by starting with A-Rod and adding another catcher later.

NFL survivor pool - week 8 and 9 strategy

I'm heading to Hawaii tomorrow for ~2 weeks, and I'm not bringing my computer, so I'm going to discuss weeks 8 and 9 now.

In week 8 I think you should go with San Diego (vs. Oakland) or Chicago (vs. Cleveland). Both of these teams are huge favorites this week and neither team has any games remaining on their schedules worth saving them for.

In week 9, Indianapolis and New Orleans have the biggest projected blowouts on the schedule. However, the next few options are good as well and New Orleans and Indianapolis both need to be saved for future weeks when they will be the only good options. So, in week 9 I'd go with San Francisco or New England who will be playing their easiest game left on their 2009 schedules.

So, pretty simple stuff, right? I'll see you for week 10!

2009 NFL Survivor Elimination Pool - Week 7 Pick Strategy

1. Please decide if you think your pool will last beyond week 12. If so, please read on in this paragraph, if not please skip to the next paragraph (This is important, b/c if your pool is going to last past 12 you will need to save the Pats and Colts for those weeks). If you're pool has more than 20 left, you should definitely be reading this paragraph. Your best option in week 7 is to use the Giants. If you've already used the Giants (which most of you have), then use Green Bay this week. If you've already used Green Bay, then you're next best option is New Orleans.

2. If your pool has less than 10 people left, you should definitely be reading this paragraph. Your best choice this week is the Colts, followed the Patriots. Warning, you will have no good choices if you survive to week 13.

NFL 2009 Survivor Pool - Updated Week 7 Team Rankings

Lot of shifts in the updated team valuation. Week 7 pick recommendations coming soon. Here are updated results:

Team	Yards/Game Differential	Points/Game Differential	ESPN Power Rank	Yard Index	Points Index	Power Rank Index	Final Score
NO	128.8	19.8	2	95.0	100.0	96.8	97.3
IND	109.2	13.2	1	88.7	83.1	100.0	90.6
NYG	144.3	9.9	5	100.0	74.6	87.1	87.2
DEN	106.2	11.2	4	87.8	77.9	90.3	85.4
NE	111.4	12.0	6	89.4	80.0	83.9	84.4
PIT	128.5	4.6	8	94.9	61.0	77.4	77.8
MIN	6.4	11.3	3	55.8	78.2	93.5	75.8
PHI	68.8	7.4	12	75.8	68.2	64.5	69.5
BAL	60.5	6.5	11	73.1	65.9	67.7	68.9
GB	61.6	7.4	13	73.5	68.2	61.3	67.7
ATL	-31.4	9.2	7	43.6	72.8	80.6	65.7
CHI	12.6	4.0	10	57.8	59.5	71.0	62.7
DAL	62.6	4.8	19	73.8	61.5	41.9	59.1
CIN	-22.9	0.0	9	46.4	49.2	74.2	56.6
ARI	13.0	4.0	16	57.9	59.5	51.6	56.3
HOU	17.7	1.0	17	59.4	51.8	48.4	53.2
NYJ	15.4	1.7	18	58.7	53.6	45.2	52.5
MIA	38.6	1.2	20	66.1	52.3	38.7	52.4
SD	-16.6	-2.4	14	48.4	43.1	58.1	49.8
SF	-55.6	2.8	15	35.9	56.4	54.8	49.0
SEA	-9.5	1.5	23	50.7	53.1	29.0	44.3
JAC	-5.5	-4.5	21	52.0	37.7	35.5	41.7
WAS	7.0	-2.8	27	56.0	42.1	16.1	38.0
CAR	-16.0	-8.0	22	48.6	28.7	32.3	36.5
BUF	-61.3	-6.0	24	34.1	33.8	25.8	31.2
DET	-77.6	-14.1	26	28.8	13.1	19.4	20.4
KC	-120.1	-7.7	28	15.2	29.5	12.9	19.2
OAK	-151.7	-12.9	25	5.1	16.2	22.6	14.6
TB	-92.5	-13.2	31	24.1	15.4	3.2	14.2
TEN	-94.9	-19.0	30	23.3	0.5	6.5	10.1
CLE	-167.5	-13.2	29	0.0	15.4	9.7	8.4
STL	-106.7	-19.2	32	19.5	0.0	0.0	6.5

2009 NFL Survivor Elimination Pool - Week 6 Pick Strategy

Well, the worst team (Oakland) isn’t playing on the road against the best team (New York Giants) this week, so your week 6 pick will be a little more interesting than week 5. After looking at all of the match-ups on the week 6 schedule, and computing the team score differential (after taking home field advantage into account), here are the projected blowouts:

1. JACKSONVILLE vs. St. Louis – St. Louis is the worst team that Jacksonville still gets to play at home this season. So, if your 2009 survivor pool pick set is going to include Jacksonville (and hasn’t already) this is the best week to use them. However, Jacksonville (23rd best team score) is one of the bad teams and their team score differential compared with St. Louis isn’t large enough to warrant consideration as a week 6 pick.

2. WASHINGTON vs. Kansas City – Washington’s situation in week 6 is similar to Jacksonville’s in that Kansas City is the worst team Washington still gets to play at home this season. And, as was the case with Jacksonville, Washington isn’t a good enough team to ensure a victory even playing at home against the worst teams. So, don’t look for Washington or Jacksonville to get any more mentions in future week’s recommended pick post.

3. CINCINNATI vs Houston - Cincinnati is good (4-1 record, 9th best team score) and Houston is bad (21st best team score), but later this season Cincinnati still gets to play Cleveland, Detroit, and Kansas City (in weeks 12, 13, and 16), all at home, and all three of those teams are worse than Houston. So week 6 is not the time to use Cincinnati.

4. Philadelphia vs. OAKLAND – (Skip this paragraph if you’ve used Philly already) Philadelphia is the only road team under consideration this week. Looking through Philly’s remaining 2009 schedule, their only other “easy” win on the schedule might be Washington at home in week 12. But, also in week 12, Atlanta has Tampa Bay at home and Dallas has Oakland at home. So if you don’t pick Philly this week, you might not ever use them (which isn’t necessarily a bad thing).

5. NEW ENGLAND vs. TENNESSEE. Besides this game, New England has two other “easy” wins remaining on their 2009 schedule: Carolina at home in week 14 and Jacksonville at home in week 16. However, in the latest team rankings, Tennessee is worst than Jacksonville and Carolina (hard to believe a 13-0 team from 2008 has fallen so far!). Assuming you have already picked Baltimore, my model is telling me to save New England for week 14. If you still have Baltimore available, then you might not ever need New England.

6. NEW YORK JETS vs. Buffalo. The Jets have a predicted win coming up this week. However, their match-up does not have the largest disparity. That seems to be a pattern with the Jets. Looking through their remaining schedule, they also have Carolina and Jacksonville at home, however, there always seem to be even bigger blowouts to choose from those weeks. It doesn’t look like the Jets are making it into the model at all this week.

7. GREEN BAY vs. Detroit – Detroit is the worst team that Green Bay still gets to play at home this season. So, if your 2009 survivor pool pick set is going to include Green Bay and hasn’t already, this is the best week to use them. But I think there are better match-ups this week.

8. PITTSBURGH vs. Cleveland – I saved my recommended pick for last. This isn’t actually Pittsburgh easiest game remaining on the 2009 schedule. They also get Oakland at home in week 13 and Oakland (ranked dead last) is even worse than Cleveland (ranked 5th to last). However, also in week 13 the Colts have the Titans at home, which is an even wider disparity game than Pittsburgh and Oakland. So my model tells me that this is the time to use Pittsburgh, even though it’s not their easiest game remaining. This match-up is a wider disparity than the first 7 mentioned, even though it isn’t Pittsburgh’s widest disparity on their remaining schedule. If you’ve already used Pittsburgh, the model says Philadelphia is the next best option.

NFL 2009 Survivor Pool - Updated Week 6 Team Rankings

After 5 weeks of football, here are the updated team valuations. Stay tuned for the week 6 pick in the next day or two.

Team	Yards/Game Differential	Points/Game Differential	ESPN Power Rank	Yard Index	Points Index	Power Rank Index	Final Score
NYG	206.8	16.0	2	100.0	91.6	96.8	96.1
NO	119.0	19.5	4	77.9	100.0	90.3	89.4
IND	109.2	13.2	1	75.4	85.0	100.0	86.8
DEN	124.0	11.2	5	79.2	80.2	87.1	82.1
PHI	96.5	10.3	7	72.2	78.0	80.6	77.0
MIN	12.0	13.2	3	51.0	85.0	93.5	76.5
BAL	68.2	8.2	11	65.1	73.0	67.7	68.6
ATL	-9.3	9.7	8	45.6	76.6	77.4	66.5
CIN	7.8	2.2	6	49.9	58.7	83.9	64.2
PIT	85.0	3.0	13	69.3	60.6	61.3	63.7
NE	47.0	2.6	10	59.8	59.7	71.0	63.5
NYJ	-5.2	2.6	9	46.6	59.7	74.2	60.2
CHI	-14.2	6.8	12	44.4	69.7	64.5	59.5
DAL	62.6	4.8	17	63.7	64.9	48.4	59.0
GB	5.5	2.7	14	49.3	59.9	58.1	55.8
SEA	31.8	6.6	20	55.9	69.2	38.7	54.6
MIA	38.6	1.2	18	57.7	56.3	45.2	53.0
SF	-55.6	2.8	15	33.9	60.1	54.8	49.6
SD	-16.5	-0.2	16	43.8	53.0	51.6	49.5
ARI	-37.7	-1.0	19	38.4	51.1	41.9	43.8
HOU	-14.0	-1.0	22	44.4	51.1	32.3	42.6
WAS	9.0	-1.8	24	50.2	49.2	25.8	41.7
JAC	-52.6	-6.0	21	34.7	39.1	35.5	36.4
BUF	-50.0	-7.8	25	35.3	34.8	22.6	30.9
CAR	-39.3	-11.7	23	38.0	25.5	29.0	30.9
TEN	-27.2	-11.0	27	41.1	27.2	16.1	28.1
DET	-36.0	-11.8	26	38.9	25.3	19.4	27.8
CLE	-131.8	-13.2	28	14.8	22.0	12.9	16.5
TB	-95.6	-14.4	31	23.9	19.1	3.2	15.4
KC	-144.8	-10.8	30	11.5	27.7	6.5	15.2
STL	-82.0	-22.4	32	27.3	0.0	0.0	9.1
OAK	-190.4	-16.2	29	0.0	14.8	9.7	8.2

2009 NFL Survivor Elimination Pool - Week 5 Pick Strategy

Let's review all of the projected blowouts and large point spread games of week 5 and see which ones might make for a good week 5 pick.

1. Cincinatti @ Baltimore - Baltimore is a 9 point favorite. However, see the team scores below. Baltimore is one of the best teams at 82 points and Cincinatti is above average with 54 points. If you didn't use Baltimore in week 3 when they hosted Cleveland, I would recommend saving them for week 14 when they host Detroit, and you will see as you read on that there are better blowouts to choose from this week.

2. Pittsburgh @ Detroit - Pittsburgh is a 10.5 point favorite. Pittsburgh is scored a 64 below and Detroit is 23. However, you should save Pittsburgh for next week (week 6) or week 13 when they host Cleveland and then Oakland as these two teams are even worse than Detroit, and Pittsburgh gets to play them at home, and you will see there are even better options mentioned below.

3. Minnesota @ St. Louis - Minnesota is a 9.5 point favorite. St. Louis is currently the worst team, but why pick Minnesota on the road in week 5 when you can pick them at home in week 10 against Detroit?

4. Dallas @ KC - Dallas is a 9 point favorite. KC is quite bad, but once again we see that later in the season Dallas has a matchup at home against an equally bad team, Oakland, in week 12.

And now for the best two options of the week:

5. If you have the NY Giants available, this is the perfect week to use them. They are hosting Oakland, which is the worst team they have left to face on their 2009 schedule. Unlike with the first 4 matchups discussed, there is no good reason to save this favorite.

6. If you've already used the NY Giants (or don't think Eli's foot will hold up this week), your next best alternative in week 5 is to use Philadelphia at home against Tampa Bay. Tampa Bay is the worst team remaining on the Eagles' 2009 schedule, so just like with the Giants, there is no better week to use the Eagles than now in week 5.

The model prefers the Giants this week over the Eagles because Oakland and Tampa Bay are almost equally bad, but the Giants are the #1 team (see previous post) and the Eagles are (only) #6.

In the rare event you have already used NYG and Philly, the model is telling me that Minnesota is the best choice of those first 4 games mentioned.

NFL 2009 Survivor Pool - Updated Week 5 Team Rankings

Before posting week 5 pick recommendations I wanted to share the updated team rankings (which are an ever changing/evolving input into my Excel survivor pool pick optimizer). As you know from the earlier post, each team's score is based on their point per game differential, yards gained minus yards allowed per game, and ESPN power rank. The table below has all of these things plus each team's final score in the rightmost column. The teams are listed from best to worst.

Team	Yard Differential	Point Differential	ESPN Power Rank	Yard Index	Points Index	Power Rank Index	Final Score
NYG	168.7	10.8	2	100.0	78.5	96.8	91.8
NO	119.0	19.5	4	84.3	100.0	90.3	91.5
IND	106.0	11.0	1	80.2	79.0	100.0	86.4
DEN	125.2	13.3	8	86.3	84.7	77.4	82.8
BAL	121.7	11.0	7	85.2	79.0	80.6	81.6
PHI	121.3	7.3	10	85.0	69.9	71.0	75.3
MIN	20.7	9.5	3	53.3	75.3	93.5	74.1
NE	88.5	4.0	6	74.7	61.7	83.9	73.4
NYJ	19.5	4.2	5	52.9	62.2	87.1	67.4
PIT	104.0	1.8	15	79.6	56.3	54.8	63.6
SF	-20.0	12.2	12	40.5	82.0	64.5	62.3
CHI	-14.2	6.8	14	42.3	68.6	58.1	56.3
GB	5.5	2.7	13	48.5	58.5	61.3	56.1
DAL	29.7	4.5	17	56.2	63.0	48.4	55.8
CIN	-26.8	2.0	11	38.3	56.8	67.7	54.3
ATL	-78.3	1.3	9	22.1	55.1	74.2	50.4
SD	-16.5	-0.2	16	41.6	51.4	51.6	48.2
JAC	-20.7	2.8	18	40.3	58.8	45.2	48.1
MIA	22.3	0.5	21	53.8	53.1	35.5	47.5
WAS	23.8	-1.5	22	54.3	48.1	32.3	44.9
HOU	-36.5	0.5	20	35.3	53.1	38.7	42.4
ARI	-25.0	-3.7	19	38.9	42.7	41.9	41.2
SEA	-5.3	-2.0	24	45.1	46.9	25.8	39.3
TEN	-3.5	-8.2	25	45.7	31.6	22.6	33.3
BUF	-86.2	-9.0	23	19.6	29.6	29.0	26.1
DET	-42.7	-12.7	27	33.3	20.5	16.1	23.3
CAR	-69.0	-16.7	26	25.0	10.6	19.4	18.3
OAK	-148.3	-11.0	28	0.0	24.7	12.9	12.5
KC	-132.5	-12.0	30	5.0	22.2	6.5	11.2
TB	-114.0	-13.3	31	10.8	19.0	3.2	11.0
CLE	-141.0	-17.2	29	2.3	9.4	9.7	7.1
STL	-108.2	-21.0	32	12.6	0.0	0.0	4.2

2009 NFL Survivor Elimination Pool - Week 4 Pick Strategy

Entry Name	Week 1	Week 2	Week 3	Week 4 Recommendation
Tony/Cody	BAL	WAS	PHI	SF
Johnny	IND	WAS	BAL	SF
Ryan	GB	WAS	BAL	SF
Anonymous	NO	WAS	BAL	SF

My week 4 recommendation for everyone is to use San Franciso this week (They are playing at home against St. Louis. SF, according to the updated team scoring system posted yesterday, is the 17th best team and St. Louis is the 31st. The SF 49ers only other predicted blowout on the schedule is in week 16 when they host the Detroit Lions. But Detroit (despite recently losing about 20 games in a row over 3 calendar years) is actually a much better team right now than St. Louis, so there is no better week to use SF than right now in week 4.

Many of you will be wondering about the other options this week: Chicago (at home against Detroit), Indianapolis (at home against Seattle), and NY Giants (on road against KC) are all good options as well. However, using the updated team valuations from yesterday's post. The difference in scores between SF and St. Louis (after taking home field advanatage into account) is larger than the disparity in any of the other games mentioned.

If you are considering going with either the Giants, Bears, or Colts instead of the SF 49ers, here are some more things to consider:

I would save NY Giants for week 5 when they are home against the Oakland Raiders. The Raiders are almost just as bad as KC, so better to wait for week 5 to use the Giants when they are at home instead of this week on the road.

The model is saying to save the Bears for week 8 when they host the Cleveland Browns. The Browns are the worst team in the NFL by far. So the Bears are more likely to win in week 8 than this week against the Lions.

The model is saying to save the Colts (4th best team) for week 7 when they are on the road aginst St. Louis (31st best team). In week 7, they will be even more likely to win than they are this week against the Seahawks (18th best team).

Questions/Comments?

2009 NFL Survivor Elimination Pool - Updated Team Rankings

A few of the comments have questioned my model because it was based on ESPN's power rankings. For the first few weeks of the season, I think it was a good idea to base the optimization model on the power rankings because what else do you have to go by? It just doesn't make sense to use last year's team statistics or 2009 preseason statistics. So I went with the power rankings which told me that going into week 1 the defending Super Bowl champs Pittsburgh were the best team and the 0-16 Lions were the worst, which made a lot of sense at the time.

However, there are several areas in which using the power rankings leaves something to be desired. For example, what if two teams (such as Tampa Bay and St. Louis) are equally good or bad? Power rankings force one of them to be ranked better than the other. Also, rankings force teams to be given incremental ranks from 1 to 32, but what if the best team is twice as good as the 2nd best team? Power rankings force the model to believe that the best team is as equally likely to beat the 2nd best team as the 31st team is to beat the 32nd team.

So, 3 weeks into the season, I think it's time to incorporate some 2009 NFL team statistics into the model. So before calculating the week 4 picks, I've made a few enhancements to the model. Each team's score (which is the essential input to the model which gets updated every week) will now be calculated based on three metrics:

1. Yards gained minus yards allowed per game (Yard Differential)
2. Point differential per game
3. ESPN power rankings

I began with yard differential / game which is the yards gained per game minus the yards allowed per game. Denver (160 more yards gained than allowed per game) is the best and Cleveland (195 more yards allowed than gained per game) is the worst team at yard differential so far this season. But yard differential / game isn't everything. I wanted to incorporate turnovers and red zone offensive and defensive proficiency which is where the point per game differential comes into play. The Saints are the best team so far in point differential per game, averaging 21 more points scored than allowed through week 3.

Finally, if I would have counted point differential/game and yard differential per game equally, the Saints would have come out as the best team going into week 4. This is why the power rankings are still incorporated into the model, b/c they provide a nice grounding (The saints are now power ranked 4th btw)

So these three metrics are all indexed meaning each of the 3 metrics is re-scaled so that the best team gets a score of 100 and the worst team a score of 0. A team's final score will be their average score across the 3 metrics. Here is how the final score was calculated for all 32 teams (remember, these scores will be re-calcualted every week):

Team	Yard Differential	Point Differential	ESPN Power Rank	Yard Index	Points Index	Power Rank Index	Final Score
BAL	147.6	16.6	1	96.6	89.1	100.0	95.3
NO	125.7	21.3	4	90.4	100.0	90.3	93.6
NYG	146.4	10.7	3	96.3	75.5	93.5	88.4
IND	90.7	9	2	80.6	71.6	96.8	83.0
DEN	159.6	15.4	13	100.0	86.4	61.3	82.6
MIN	57.6	10.3	5	71.2	74.6	87.1	77.6
NE	132.7	3.3	7	92.4	58.4	80.6	77.2
PHI	121.3	7.3	9	89.2	67.7	74.2	77.0
NYJ	59.0	10.3	6	71.6	74.6	83.9	76.7
SD	60.0	3	12	71.9	57.7	64.5	64.7
DAL	47.0	8.4	17	68.2	70.2	48.4	62.3
GB	-22.7	6	10	48.5	64.7	71.0	61.4
CHI	21.7	1	14	61.1	53.1	58.1	57.4
PIT	56.7	-1	16	71.0	48.5	51.6	57.0
CIN	-29.0	1.6	11	46.8	54.5	67.7	56.3
ATL	-78.3	1.3	8	32.9	53.8	77.4	54.7
SF	-43.7	4.6	15	42.6	61.4	54.8	53.0
SEA	43.6	3	23	67.3	57.7	29.0	51.3
TEN	16.4	-4.4	18	59.6	40.6	45.2	48.5
ARI	-25.0	-3.7	19	47.9	42.3	41.9	44.0
WAS	15.6	-3	26	59.4	43.9	19.4	40.9
JAC	-49.0	-3	22	41.1	43.9	32.3	39.1
BUF	-71.7	-2.7	21	34.7	44.6	35.5	38.3
MIA	-13.7	-8.7	24	51.1	30.7	25.8	35.9
HOU	-103.0	-7	20	25.9	34.6	38.7	33.1
DET	-97.7	-9	28	27.4	30.0	12.9	23.4
CAR	-69.0	-16.7	25	35.5	12.2	22.6	23.4
OAK	-143.0	-7	27	14.6	34.6	16.1	21.8
KC	-98.0	-12.3	30	27.3	22.4	6.5	18.7
TB	-136.0	-16.6	31	16.6	12.5	3.2	10.8
STL	-127.3	-16.3	32	19.0	13.2	0.0	10.7
CLE	-194.7	-22	29	0.0	0.0	9.7	3.2

So these are the week 4 scores which will go into the model. Let me know your comments. I will share the model's week 4 picks sometime tomorrow.

2009 NFL Survivor Elimination Pool - Week 4 update

All our week 3 picks won easily. Week 4 picks will be coming up either tomorrow (Tuesday) or Wednesday. If anyone else is alive and has a different set of winners than the ones listed below, then let me know which winners you have used and I'll let you know what the model says for your week 4 pick as well.

Entry Name	Week 1 Winner	Week 2 Winner	Week 3 Winner
Tony/Cody	Baltimore	Washington	Philadelphia
Johnny	Indianapolis	Washington	Baltimore
Ryan	Green Bay	Washington	Baltimore