Orton's Arm

In this case, the difference will be statistically insignificant due to a low sample size (4.5 games last year, 7 games this year) and due to the high level of variance in each sample. In 2006, for example, Losman helped the team score 17 points in the Jets game, but just 6 points in the second New England game. This creates a lot of uncertainty about how many points the Losman of 2006 will help the team score in the next game. The definition of "noise" is very broad, and includes differences in the quality of the defenses Losman faced, differences in playcalling, differences in the play of the supporting cast, differences in weather conditions, and everything else along those lines. Please believe me when I say that "noise" could very easily account for quite a bit more than the 7% change we're looking at. As for other QBs' stats, it's not necessary to bring them into this particular discussion. The question at hand is whether Losman is playing better this year than he did in his second stint last year.

To test for statistical significance, I'd need to create a t-distribution for his adjusted points from last year (at a 15 yard threshold), and compare that to the t-distribution for his adjusted points from this year. I could go through all that, but I already know what answer it would give me. The difference won't be statistically significant. But even if there was a statistically significant difference (which there wouldn't be), what, precisely, would that mean? Especially, what would it mean in light of the fact that his adjusted points per game at a ten yard ratio was actually higher in his second stint of 2005 than it's been this year?

Golf. Just kidding. Of market research. Mostly he focused on statistical analysis of market research data.

By "big enough" I mean "likely to be statistically significant." Generally, small differences are likely to be due to noise. So the slight decrease in yards per attempt probably doesn't mean Losman is doing worse, just as the slight increase in adjusted points per game (using a 15 yard threshold) probably doesn't mean Losman is doing better. Either or both of these trends could easily be wiped out by his next game. Whether you use a 10 yard threshold or a 15 yard threshold, it's very hard to use the adjusted points per game stat to make the case that Losman is doing significantly better this year than he was in his second stint last year.

A professor in a subject which involves a lot of statistical analysis.

Even using a 15 yard threshold, Losman's only increased his points per game by 7% this year versus his second stint from last year. That's not a big enough increase to demonstrate meaningful improvement. Add to that the fact that his yards per attempt is slightly lower this year than it was last year, his TD/INT ratio is about the same, and you're looking at numbers which don't support the idea that he's improved. I guess you could use completion percentage to make the case he's improved, if you're willing to overlook the ways completion percentage can be inflated. Or you could use the eyeball test, at least if your eyes saw something different than mine. Or you could make the claim that this year's circumstances are worse than last year's. If that was the case, stable numbers would indicate improving performance. But this year the offensive line is, um, less bad than it was last year, and the playcalling is better. Eric Moulds is gone, but that's partially negated by the Robert Royal upgrade at TE.

Show me where I've made the claim that I know more about statistics than, for example, you know or Ramius knows. I haven't offered an analysis of the problem yet, so your criticism is premature. My intention in starting this thread was to have an intelligent conversation about statistics, in a less emotional atmosphere than a thread about eugenics would have created. Partly I saw this thread as an opportunity for people to prove they understand the subject on a deeper level than, for example, the statistics-oriented professor I mentioned earlier. I also saw it as a chance for people to get an accurate measure of how well I understand the topic, instead of making the type of assumptions I've sometimes seen.

Suppose the chess club brought you in at the beginning. All they could afford was a survey. They asked you to write the survey questions, and interpret their results. They want to know which things (such as free snacks) would be most helpful in increasing membership. How would you go about helping them answer this question?

Lol, no, the 2005 numbers were ones I crunched before the season began. Going through the play-by-play is a pain in the neck, and I was too lazy to do it a second time. I had to draw the line somewhere, and I figured 10 yards was enough for a first down. I didn't realize that there were more 10 - 20 passing yard drives last year than there've been this year. Good find.

I was wondering how those stats compared to those for other quarterbacks. In the process of looking for aggregate QB stats, I came across this breakdown from Football Outsiders. Their system has Losman ranked 29th out of 36 QBs.

Enjoy. http://www.bluemountain.com/view.pd?i=1494...y&source=bma999

Do you have numbers with which to back up this statement? As for the numbers you provided, they could show one of three things: Losman's doing an above-average job of creating first downs, McGahee & company are doing a below average job, or the Bills are disproportionately likely to pass in 2nd and 2 or 3rd and 2 type situations.

You may well be right, but I hope the Bills aren't as short-sighted as you describe. This team hasn't had a real QB since Jim Kelly left. We've tried too many half measures (Todd Collins, Billy Joe Hobart) and too many quick fixes (Doug Flutie, Drew Bledsoe). There have also been too many missed opportunities. The Bills could have traded up for Chad Pennington in 2000, but instead decided to draft Erik Flowers in the 1st, Travares Tillman in the 2nd, and Corey Moore in the 3rd. And just as the Bills decided to give Johnson another year back in 2000; they chose to give Losman another year this year. Time will tell if the lost Cutler/Leinart opportunity will be more or less painful than the lost Pennington opportunity turned out to be. The problem the Bills have had at QB is twofold: because the position has been broken since Kelly left, the Bills have kept dumping draft picks into it. The second problem is that those draft picks have been invested unwisely, so we usually haven't had better results at QB than a low priced free agent such as Holcomb could have produced. Yes, the Bills need to address the offensive line. But that does not negate the need for a quarterback. If Losman doesn't prove anything in the rest of the season, I sincerely hope the Bills address the position in the draft. Preferably with their first round pick.

But the Bills haven't been sustaining drives. I saw a statistic about the percentage of third downs that actually get converted when a team chooses to pass. Guess which team was at the very bottom of the list? The problem I have with completion percentage is that you can game the system. If it's 3rd and 10, throw a 5 yard pass. That'll help your completion percentage and passer rating, but it won't do much to help the team. Ultimately, a QB's job is to help the offense score points. To figure out how many points Losman was helping the offense score, I started with the raw number of points per game the Bills scored. Then I did the following: - Weeded out points scored by the defense and special teams - Weeded out points scored by the offense when Losman contributed less than ten yards - Deducted three points from any scoring drive that started in field goal range After making these adjustments, Losman helped the offense score 12.2 points per game in his second stint of 2005. This year, and again making these adjustments, he's helped the offense score 11.1 points per game. So yes, he's playing better than his first stint of 2005, but I don't see too many meaningful measures which would say he's playing better than his second stint. Not points per game, not yards per attempt, not TD/INT ratio, and not the eyeball test.

The experiment you've designed would produce solid results. However, the chess club that could afford such an expensive experiment would be rare indeed. In this example, the chess club was only able to afford a survey. It's looking at offering a number of different things (one of which is free snacks), but it can only afford to offer a few of the things it's considering. It wants to know which things it should offer to increase membership. While the chess club realizes the results won't be as reliable as they could have been with the experiment you describe, it at least wants you to use the survey data to tell it something. Am I correct in concluding you'd use method 2, except that you'd throw out the Interested data instead of the Uninterested data?

Welcome to the boards. Some people around here seem to feel that if the offensive line is a need--and it clearly is--QB can't possibly be a need too. Expect to hear a little criticism from such people, even despite what you said about wanting OL. As for myself, I'd welcome the Bills taking a QB in the first round, at least if I thought he'd be a quality starter for the next ten years.

And, you, sir, have omitted a very important statistic that would hurt your argument. '05* 134 Att 904 yards 6.8 yards per attempt * 5 games cited above '06 197 Att 1312 yards 6.7 yards per attempt Yes, his completion percentage is higher, but he's not getting more yards per attempt. To me this shows that the playcalling has shifted towards shorter, safer, higher percentage passes, thereby increasing Losman's completion percentage and passer rating. But the stable yards per attempt stat suggests he's not doing a more effective job moving the offense down the field than he did in those 4.5 games last season. Does that pass the eyeball test? Well, the Losman we've gotten this year--and in particular the Losman we've gotten the last few weeks--sure doesn't look a whole lot more effective than the Losman who played those five games last year.

When you present the numbers that way, it doesn't look like he's made that much progress at all. And when you watch him play, it just seems like there's something missing. Especially these last few weeks.

Chicken! On a more serious note, I guess my earlier post came out the wrong way. I probably shouldn't have said anything beyond the fact that I'll take my hat off to whichever people get the question right. So post an answer or not, as you please. But I'd at least encourage you to work the problem out for yourself. Once you clearly see which answer is the right one, and why, it's a really good feeling.

Patience. There are a few people I may need to accuse of chickening out of this question. I can't really make that accusation unless I give them a fair chance to answer. In particular, I've accused Ramius of not having the intellectual depth with which to back up his often vitriolic style of posting. In the spirit of fair play, I felt I'd offer him a chance to show that Bungee Jumper was right about him, and that I was wrong.

So I'd be glad to hear anything you have to say about the statistics question in my initial post. If you like to address me about a different topic, do so in another thread.

Sorry to laugh at the egg on your face, VA Bills. But that's exactly what you deserve for trying to turn a perfectly good statistics thread into yet another name calling contest. As though the PPP board needs less statistics and more namecalling. Does anyone besides Meazza feel brave enough and smart enough to choose between method 1 and method 2?

I voted for Cutler. While both Leinart and Cutler may well have successful careers, Cutler's arm would give him an edge in windy Ralph Wilson Stadium.

During the eugenics debate, a few of my adversaries made the erroneous claim that I don't understand statistics. I'm a little curious as to how well these people actually understand the subject themselves, so I'll pose a little test. I've already seen a statistics-oriented professor get this one wrong, so I won't automatically assume that anyone who does this for a living will get the right answer. Here goes. A survey is given out to people. Its intention is to determine which factors influence a person's decision to join the chess club. One of the questions is, "upon entering college, did you seriously consider joining the chess club? Yes or No." Based on the responses to that question, people were divided into the Interested and Uninterested groups. Both groups of people were also asked a series of questions of the following type: "On a scale from 1 - 5, how much would free snacks have influenced your decision to join the chess club?" The chess club wants to know the extent to which free snacks will influence someone's decision to join. There are two methodologies for determining this, but only one is correct. Method 1: Separate the survey respondents into Interested and Uninterested. See if there's a statistically significant difference between the two groups' preference for snacks. If there is, and if Interested people are significantly more likely to prefer snacks than Untinterested people, it's a signal that a preference for snacks is causing people to join the chess club. Ergo, the chess club should offer free snacks. Method 2: Separate the survey respondents into Interested and Uninterested. Ignore those who are Uninterested. Whichever things the Interested group said would make the biggest difference; these the chess club should do.

I'm not surprised by this decision after having watched Romo play. There were a few times when he looked clueless. Those three interceptions he threw were entirely his fault. But for the most part, he took total command of the Cowboys' offense, and willed it down the field. His presence and his play brought a moribund Cowboys' offense to life. He's not happy with how he played, and he said as much in the press conference. If he's as interception-happy in the coming weeks as he was against the Giants, he'll go back to the bench. But if he cuts back on those INTs, and if he maintains the positive aspects of his play, the Cowboys will have a real QB.