In five years, 5-1 (1 Viewer)

[moleculo]

*Shanny's playcalling has always given the Pats/BB fits. It's very apparent he can diagnose the Pats weaknesses and explot them, especially on third down. He doesn't do anything too fancy, he just takes what the Patriots give him and doesn't get too greedy. On defense they have had success at the line of scrimmage and have usually not allowed the Pats to establish an offensive identity. As far as the game the Pats won a few years ago...as painful as it is to admit it if Danny Kannell's not behind center than it could have been a different story.

regarding that Monday night game - in my foggy recollection, the game was lost by Deltha O'Neill, and that was the beginning of the end for him in Denver. He was the one who bobbled the free kick after the safety, pinning Denver deep in their own end. On the Pat's next posession, Deltha was the one who got burned (badly, IMO) for the go ahead TD.It is very possible that I'm wrong, but I don't think Deltha played another meaningful game for the Broncos. Shortly after that, he was basically excluded from defensive meetings, and so he started working with the offense, and there was speculation he might see time as a WR. At the end of the season, he found himself a Bengal.That game was pretty important to ensure that Denver wouldn't have to go to Indy. They lost, and the rest is history.

 

[The Jerk]

Bill Belichick is skeletors b!@tch

Why do you hate the Patriots so much? I've noticed that you take every chance you get to say something negative about the Pats. That would be fine if you had an objective point of view, but I sense some real anger coming from you every time the Patriots are discussed. Just curious. TIA.

It's not an exclusive thing. The Scientist also takes a shot at the Steelers any time it's a possibility.

Interesting, I hadn't noticed that.Taking shots at the Pats and the Steelers at every turn... I'll guess maybe he's a Browns fan?

Seahawks.

 

[SSOG]

Am I the only one who thinks it's too small a sampling size to talk ownage?

If they each have a 50% chance of winning each game, one team or the other will win at least 5 out of 6 games about 22% of the time. So there's nothing statistically significant going on here.

Go back to the beginning of the Elway era and I'm pretty sure that Denver is 13-3 against New England. Suddenly that's a lot more statistically significant.

 

[Borat]

Am I the only one who thinks it's too small a sampling size to talk ownage?

If they each have a 50% chance of winning each game, one team or the other will win at least 5 out of 6 games about 22% of the time. So there's nothing statistically significant going on here.

Go back to the beginning of the Elway era and I'm pretty sure that Denver is 13-3 against New England. Suddenly that's a lot more statistically significant.

But Belichick wasn't coaching them that whole time. Nor was Shanahan coaching Denver that whole time.

 

[Maurile Tremblay]

Am I the only one who thinks it's too small a sampling size to talk ownage?

If they each have a 50% chance of winning each game, one team or the other will win at least 5 out of 6 games about 22% of the time. So there's nothing statistically significant going on here.

are you sure? This doesn't sound right. Probability of one team winning 5 out of 5 is 3.1%, I think probability of winning 5 out of 6 should be just slightly higher than that. I'm a little rusty with my probability theory...

I'm sure. If they play six games, there are 2^6 = 64 possible combinations of outcomes. There are 7 ways for each team to win 5 or more games (it could lose the first game, or the second game, or the third game . . . or the sixth game, or it could win all the games). So there are 14 ways for at least one of the teams to win 5 games. 14/64 = 22%.

I'll buy that The obvious next question is at what probability do you set the ownage threashhold? 5%?

Five percent is standard when you're testing a hypothesis and you don't know the results yet. So if we come up with our "Shanny o\/\/ns the Patriots" hypothesis after having watched Denver win five of their last six against them, we'd test the hypothesis by looking for future ownage that is significant at the 5% level. The six games already played can't count.From Stanford Wong's book on sports betting:

[suppose you examine the reults of NFL games played from 1995-1997, and based on those results, hypothesize that NFL home dogs of +7 or more are good bets.]

The most generally used standard of statistical significance is five percent. As a close approximation, five percent rarity occurs when the W-L record of the sample you have gathered is two standard errors different from 50 percent wins.

The square root of your sample size is the standard deviation of the difference between your total wins and total losses, which I will call excess wins.

The easy way to find the number of standard errors is to divide the excess wins by the standard deviation.

You have reached that five-percent point when your excess wins is two standard errors.

For example, suppose you tested the hypothesis that NFL home dogs of +7 or more are good bets by examining the NFL home dogs played during the 1998-2000 seasons. Suppose you came up with a W-L record of 30-25.

That's a sample of 55 decisions. The square root of 55 is 7.4. Thirty wins minus 25 losses is 5 excess wins. That's less than one standard error. For 55 decisions you need a W-L record of 35-20 to have statistical significance at the five percent level.

Suppose the W-L record for NFL home dogs of +7 or more was 32-15 for games played during 1995-1997. If you add those games in, you get a record of 62-37 for the six-year period 1995-2000. Can you call that a sample of 99 decisions?

No you cannot do that. The reason is you used those 1995-1997 games to formulate and modify your hypothesis. You cannot also use them to test the hypothesis. Only the games played in years other than 1995-1997 can be used to test that hypothesis.

Wong goes on to suggest that if two standard errors is sufficient for testing a hypothesis using data different from the data that generated the hypothesis, you want four standard errors (i.e., 0.1% significance instead of 5% significance) when testing a hypothesis using the same data that generated it.

 

[((Morpheus))]

Am I the only one who thinks it's too small a sampling size to talk ownage?

If they each have a 50% chance of winning each game, one team or the other will win at least 5 out of 6 games about 22% of the time. So there's nothing statistically significant going on here.

Go back to the beginning of the Elway era and I'm pretty sure that Denver is 13-3 against New England. Suddenly that's a lot more statistically significant.

I believe if we go back that far the score stands at 3-2.

 

[msommer]

Am I the only one who thinks it's too small a sampling size to talk ownage?

If they each have a 50% chance of winning each game, one team or the other will win at least 5 out of 6 games about 22% of the time. So there's nothing statistically significant going on here.

Go back to the beginning of the Elway era and I'm pretty sure that Denver is 13-3 against New England. Suddenly that's a lot more statistically significant.

I believe if we go back that far the score stands at 3-2.

None of those specific games involved both teams. Move along

 

[PatsWillWin]

Am I the only one who thinks it's too small a sampling size to talk ownage?

If they each have a 50% chance of winning each game, one team or the other will win at least 5 out of 6 games about 22% of the time. So there's nothing statistically significant going on here.

uhh - they're playing a football game guys, not flipping coins.as a pats fan, i cna tell you that shanahan is the only guy that i don't think belichick has a substantial coaching edge over in a given game.

 

[Gatorman]

I love how this thread went from A simple conjecture about skeletor vs. BB to a pats/bronco whiny tool thread with maurile math thrown in.

Some teams just matchup better with others, regardless of how the team is composed.

Denver matches up well with the patriots.

Going back a ways: No matter how bad the Jets are, Miami has always had probelms with them

No matter how good Tenn was (in the McNair days), Miami always matched up well with them.

The Patriots own the dolphins, even though many of those games were decided very late (sometimes in OT)

No matter how good indy is, the patriots match up well with them

And on and on.

Sometimes it's scheme, sometimes it's Karma, but it happens.

Looking at any of the playoff runs for most teams in the past few years (and earlier), there are one or two plays that made the difference in their championship hopes.

Big Ben and the the Bus' fumble.

The Tuck

The immaculate reception

the holy roller

The Drive

The Fumble

Etc.