Orton's Arm Posted October 31, 2006 Share Posted October 31, 2006 apparently, HA likes getting mopped up and down the floor in multiple threads...thats the only reason for his assinine factless intelligence-less rants 821202[/snapback] You're actually defending syhuang? Dude, don't embarrass yourself. Link to comment Share on other sites More sharing options...
syhuang Posted October 31, 2006 Share Posted October 31, 2006 You're actually defending syhuang? Dude, don't embarrass yourself. 821215[/snapback] Should he defend you about omitting stats as well as omitting facts? Remind you again: Everyone can create any numbers he likes by (1) Create his own rules to omit the stats he doesn't want (2) Pick the threshold to favor him most (3) Use personal judgement to retain the stats which should be ommitted by different thresholds based on his rules (4) Simplify the whole system to favor his argement (5) Get the manufactured numbers benefit his opinion These manufactured numbers are useless and show nothing more than "I think ......". Link to comment Share on other sites More sharing options...
Wraith Posted October 31, 2006 Share Posted October 31, 2006 apparently, HA likes getting mopped up and down the floor in multiple threads...thats the only reason for his assinine factless intelligence-less rants 821202[/snapback] I can't believe I'm defending Holcomb's Arm here, but he has not committed the egregious "sins" that some have pinned on him. In fact, some of the claims are outright false (the claim above that the t-distribution was incorrectly applied, for example). Using statistical judgement to place a threshold is incredibly common in the real world and is usually necessary. The fact that tweaking the threshold in this test gives different results merely shows that the test is not sensitive enough to pick up a shift in Losman's production, or that there is no meaningful shift in Losman's production. It certainly does not mean that HA is deliberatly misleading with his statistics. Just as HA alluded to above, judgement calls are a part of statistics, so much so that there have been many tools devised to aid in that judgement (the whole topic of confidence intervals, for example, which is what HA was referring to with Alpha Level). An interesting way of examining HA's measurement system would be to apply the same standard to another QB, either one who's output is unquestionably higher than Losman's (Brady or P.Manning) or one who's output has meaningfully shifted year to year (D.Brees or E.Manning, perhaps. If HA's measurement system were truly capable, it would be able to detect the difference between Losman and Tom Brady or between Drew Brees "good" years and "bad" years. It is important to verify the location of the threshold is adequate by moving the thresold within reason and seeing whether the conclusions still hold. That's truly how you measure the adequacy of a measurement system. If can detect the difference between samples known to be different. This is coming from someone who does this sort of thing for a living. Link to comment Share on other sites More sharing options...
Orton's Arm Posted October 31, 2006 Share Posted October 31, 2006 I can't believe I'm defending Holcomb's Arm here, but he has not committed the egregious "sins" that some have pinned on him. Thank you. Your posts have been islands of knowledge and honesty in a sea of ignorance and malignant distortion. Link to comment Share on other sites More sharing options...
syhuang Posted October 31, 2006 Share Posted October 31, 2006 The main problem of HA's work is that he is not consistent. When he brings up something (for example, judgement calls), he only applies it to the data entries favoring him. Also, his threshold is what he feels right and he never mention the impact of different thresholds before being pointed out the results can be inconsistent. He also simplifies many important factors in his system (eq. drive length) and has an incomplete system. His system is basically a work in progress and needs lots of improvements. As mentioned, it never tests on other data sets. The results from his current incomplete system are invalid. As I said, everyone can create any numbers he likes with a prematured system. (1) Create his own rules to omit the stats he doesn't want (2) Pick the threshold to favor him most (3) Use personal judgement to retain the stats which should be ommitted by different thresholds based on his rules (4) Simplify the whole system to favor his argement (5) Get the manufactured numbers benefit his opinion These manufactured numbers are useless and show nothing more than "I think ......". Link to comment Share on other sites More sharing options...
Wraith Posted October 31, 2006 Share Posted October 31, 2006 Thank you. Your posts have been islands of knowledge and honesty in a sea of ignorance and malignant distortion. 821242[/snapback] Two improvements immediately jump to mind: 1) Make the threshold a fixed percentage of drive length instead of a fixed number. Something like 12.5% (1/8th - 10 yards of an 80 yard drive or 5 yards of a 40 yard drive). Thus, a very short but very crucial yardage on a short drive could be included. 2) Normalize your results by number of drives or possession time. I would use drives. This would eliminate the possibility of the quarterback being punished because the defense cannot get off the field. Link to comment Share on other sites More sharing options...
syhuang Posted October 31, 2006 Share Posted October 31, 2006 Two improvements immediately jump to mind: 1) Make the threshold a fixed percentage of drive length instead of a fixed number. Something like 12.5% (1/8th - 10 yards of an 80 yard drive or 5 yards of a 40 yard drive). Thus, a very short but very crucial yardage on a short drive could be included. 2) Normalize your results by number of drives or possession time. I would use drives. This would eliminate the possibility of the quarterback being punished because the defense cannot get off the field. 821267[/snapback] Good idea, other than these two, the system can be improved by (1) Giving partial credit to the scoring drives instead of current all or nothing method. (2) Using more than yards in box score to give players credits. For example, a QB should be given some credits if he can recongize opponents' blitz and audible a better play (pass or rush). (3) Testing more on thresholds and judgement calls to measure the impacts (4) Applying the judgement calls on all data entries instead of selected few (5) Testing the system on other data sets Once the system becomes more complete, the results can become useful. Currently, HA's system has too many questions and needs to be improved. The results from his current prematured system are useless. Link to comment Share on other sites More sharing options...
Orton's Arm Posted October 31, 2006 Share Posted October 31, 2006 Two improvements immediately jump to mind: 1) Make the threshold a fixed percentage of drive length instead of a fixed number. Something like 12.5% (1/8th - 10 yards of an 80 yard drive or 5 yards of a 40 yard drive). Thus, a very short but very crucial yardage on a short drive could be included. 2) Normalize your results by number of drives or possession time. I would use drives. This would eliminate the possibility of the quarterback being punished because the defense cannot get off the field. 821267[/snapback] I have mixed feelings about suggestion 1. Consider two FG drives, one of which goes 20 yards; the other of which goes 70 yards. In both drives, the QB's sole contribution was to complete a 12 yard pass on 3rd and 10. Is it nobler for a QB to benefit from good field position (the 20 yard drive) than from a good running game (the 70 yard drive)? Suggestion 2 is interesting. You point out that a QB shouldn't be punished because his defense can't get off the field, and I agree with that. But what about the QB who engineers long, clock-killing drives? A guy like that will have fewer drives because he's helping to kill the clock. So if you look at points per game, the clock killer QB will seem worse than he is. Your modification to points per drive would end this problem, and would judge the clock killer QB fairly. At first glance, your adjusted points per drive system seems like a clear improvement over adjusted points per game. The key is in implementation. You'd have to weed out kneel down drives, or drives where there was only enough time for two or three plays before time expired. You'd also have to eliminate drives which consisted only of running plays. At the margin you'll end up making judgement calls, "Was 53 seconds of game time, and no time outs, really a realistic opportunity for the QB to have led the offense to points?" I don't see these judgement calls as an intrinsic obstacle to the system's legitimacy, though they may lead a few contentious and unreasonable people to question its results. Link to comment Share on other sites More sharing options...
Orton's Arm Posted October 31, 2006 Share Posted October 31, 2006 Once the system becomes more complete, the results can become useful. Currently, HA's system has too many questions and needs to be improved. The results from his current prematured system are useless. Since you don't like my system, perhaps you should come up with one of your own. I'm curious to see what kind of system you create, and how this system would interpret Losman v2's performance versus his performance from this year. Link to comment Share on other sites More sharing options...
syhuang Posted October 31, 2006 Share Posted October 31, 2006 You've invested a lot of time and energy into complaining about my system. Perhaps some of this could be invested into coming up with your own system. I'm curious to see what kind of system you create, and how this system would interpret Losman v2's performance versus his performance from this year. 821310[/snapback] You mean creating a prematured system to create numbers like you did? no thanks. (1) Create his own rules to omit the stats he doesn't want (2) Pick the threshold to favor him most (3) Use personal judgement to retain the stats which should be ommitted by different thresholds based on his rules (4) Simplify the whole system to favor his argement (5) Get the manufactured numbers benefit his opinion These manufactured numbers are useless and show nothing more than "I think ......". I'd prefer to simply say "I think ..." instead of wasting time to manufacture numbers. Link to comment Share on other sites More sharing options...
Orton's Arm Posted October 31, 2006 Share Posted October 31, 2006 You mean creating a prematured system to create numbers like you did? no thanks. In other words, it's easier for you to criticize my system than it is for you to make one of your own. I thought as much. Link to comment Share on other sites More sharing options...
syhuang Posted October 31, 2006 Share Posted October 31, 2006 In other words, it's easier for you to criticize my system than it is for you to make one of your own. I thought as much. 821335[/snapback] You made a mistake again. You forgot to put "prematured" between "my" and "system". As I said, the results from a prematured system like yours show nothing more than simply saying "I think......". Next time, Just state what you think instead of showing invalid numbers from a prematured system to act like you have some manufactured stats to back your argument up. Everyone can create any numbers he likes with a prematured system. (1) Create his own rules to omit the stats he doesn't want (2) Pick the threshold to favor him most (3) Use personal judgement to retain the stats which should be ommitted by different thresholds based on his rules (4) Simplify the whole system to favor his argument (5) Get the manufactured numbers benefit his opinion These manufactured numbers are useless and show nothing more than "I think ......". Link to comment Share on other sites More sharing options...
Wraith Posted October 31, 2006 Share Posted October 31, 2006 I have mixed feelings about suggestion 1. Consider two FG drives, one of which goes 20 yards; the other of which goes 70 yards. In both drives, the QB's sole contribution was to complete a 12 yard pass on 3rd and 10. Is it nobler for a QB to benefit from good field position (the 20 yard drive) than from a good running game (the 70 yard drive)? Suggestion 2 is interesting. You point out that a QB shouldn't be punished because his defense can't get off the field, and I agree with that. But what about the QB who engineers long, clock-killing drives? A guy like that will have fewer drives because he's helping to kill the clock. So if you look at points per game, the clock killer QB will seem worse than he is. Your modification to points per drive would end this problem, and would judge the clock killer QB fairly. At first glance, your adjusted points per drive system seems like a clear improvement over adjusted points per game. The key is in implementation. You'd have to weed out kneel down drives, or drives where there was only enough time for two or three plays before time expired. You'd also have to eliminate drives which consisted only of running plays. At the margin you'll end up making judgement calls, "Was 53 seconds of game time, and no time outs, really a realistic opportunity for the QB to have led the offense to points?" I don't see these judgement calls as an intrinsic obstacle to the system's legitimacy, though they may lead a few contentious and unreasonable people to question its results. 821309[/snapback] Your third paragraph is true and interesting. I'll think about it. Did you get my response to your question in PM? My messaging doesn't seem to be working right and I'm not sure if the response went through. Link to comment Share on other sites More sharing options...
2020 Our Year For Sure Posted November 1, 2006 Share Posted November 1, 2006 You made a mistake again. You forgot to put "prematured" between "my" and "system".821336[/snapback] Actually, its his system, whether its "prematured" or not. You're both correct. Link to comment Share on other sites More sharing options...
syhuang Posted November 1, 2006 Share Posted November 1, 2006 Actually, its his system, whether its "prematured" or not. You're both correct. 822162[/snapback] Look carefully, it's putting "prematured" between "my" and "system" in his post: it's easier for you to criticize my system Link to comment Share on other sites More sharing options...
ganesh Posted November 1, 2006 Share Posted November 1, 2006 In other words, it's easier for you to criticize my system than it is for you to make one of your own. I thought as much. 821335[/snapback] He can be a good Politician..... Link to comment Share on other sites More sharing options...
syhuang Posted November 1, 2006 Share Posted November 1, 2006 He can be a good Politician..... 822191[/snapback] Not without the ability to create any stats through prematured systems. Link to comment Share on other sites More sharing options...
2020 Our Year For Sure Posted November 1, 2006 Share Posted November 1, 2006 Look carefully, it's putting "prematured" between "my" and "system" in his post: it's easier for you to criticize my system 822177[/snapback] Exactly. You said he made a mistake by not adding "prematured" in between "my" and "system". I'm just saying he didn't make a mistake, he merely chose to be less descriptive than you were. Omitting an adjective isn't a mistake, its just being more general. Therefore, by calling him out on a mistake that didn't exist, you were the one making the mistake. Link to comment Share on other sites More sharing options...
syhuang Posted November 1, 2006 Share Posted November 1, 2006 Exactly. You said he made a mistake by not adding "prematured" in between "my" and "system". I'm just saying he didn't make a mistake, he merely chose to be less descriptive than you were. Omitting an adjective isn't a mistake, its just being more general. Therefore, by calling him out on a mistake that didn't exist, you were the one making the mistake. 822357[/snapback] If you did read the whole thread, you should be able to notice that his system is prematured and incomplete. Missing such an adjective may not be deemed a mistake to you, but it certainly is to me especially he was replying directly to my post. Thank you for providing your opinion. Even he said: I agree the system I've designed makes only a crude attempt to capture this distinction Link to comment Share on other sites More sharing options...
Orton's Arm Posted November 3, 2006 Share Posted November 3, 2006 Exactly. You said he made a mistake by not adding "prematured" in between "my" and "system". I'm just saying he didn't make a mistake, he merely chose to be less descriptive than you were. Omitting an adjective isn't a mistake, its just being more general. Therefore, by calling him out on a mistake that didn't exist, you were the one making the mistake. 822357[/snapback] Thanks for bringing a little fresh air into what's become a stuffy discussion. I innocently created a system, which while not perfect seemed like it could shed some light on how well a QB is doing to help his team score points. I didn't realize at the time that this system would inspire syhuang to launch a personal crusade against me. Link to comment Share on other sites More sharing options...
Recommended Posts