Jump to content


  • Content Count

  • Joined

  • Last visited

Recent Profile Visitors

176 profile views
  1. The CDC has made available estimates of excess death rates - the title references excess death rates due to COVID-19, but note that the data include the 2017-2018 flu season. During the 17-18 influenza, the expected number of deaths (roughly, the statistical average) was on the order of 60,000 in the January peak; the estimated death rate was roughly 68,000 - so an estimated 8000 excess deaths that might be attributed to the 17-18 flu. For the week of April 12, expected death rate was ~56000, the estimated death rate was >76000; 20000 or about 2.5 times the excess death rate, relative to the 17-18 flu. It is also worth noting that the excess death rate for May 12 is still statistically significant, but has dropped to something on the order of the 17-18 flu, so it does appear that the lockdown has had the desired effect. ETA : https://www.cdc.gov/nchs/nvss/vsrr/covid19/excess_deaths.htm
  2. It might also make a difference in tracking the spread of the disease. Consider this. Rumor around town is that a high school wrestling coach (in the state, not locally) has tested positive. Would if have been a carrier at the state wrestling tournament? If he was, how would you go about tracking down every one he might have been in contact with, get them proactively tested (assuming we have enough tests - we don't) and having them quarantined if they test positive? As opposed to the alternative, which would be to put out a public announcement, recommending that anyone who was at the tournament self-quarantine for a week or so. Now suppose, instead, that a coach from an NCAA team tests positive in the week or two after the national meet. There should be a complete list of essential staff from the tournament venue, and each wrestler and his teem should be able to provide a complete list of the limited family members. It should be possible to track down every person potentially exposed. Under those two scenarios, which will have the lesser chance of spreading disease to untouched communities? I worked the NAIA national indoor track meet last week, and since I was an official, I would hope that if an athlete, coach or fan tests positive in the next couple weeks, I would be on the short list to be contacted about potential exposure. Perhaps there might be resources to go through hotel guest lists and contact other potential exposures. But I'm pretty damn sure I saw some people sleeping in a car in the parking lot; who knows where they're from. Monitoring the movements of persons with potential exposure is an important tool for managing epidemics (https://www.who.int/features/qa/contact-tracing/en/)
  3. There are some guidelines in the rulebook for seeding. Perhaps the rules are vague enough to allow seed 'however you want'. Let's consider that. For the purposes of this discussion, I'm going to define a *bye* as an imaginary wrestlers that serves only as a place holder, as opposed to a real live human being who intends to compete for placement in the tournament.These, I think, are the only two entries in a bracket that need to be defined; maybe the NCAA rules will have to be rewritten to include real live human beings who wish to be entered in the bracket but have no intention for competing for placement. The rules do state how to determine that number of byes; this is straightforward enough. There were 7 imaginary wrestlers entered into a 16 man bracket, just as should be. Next, we consider the first guideline for seeding, It would appear, at least on paper, that Coleman and Sebastian meet this criteria - they both are 'attached' and have wrestled D1 varsity matches, as opposed the the rest of the field who are listed as Unattached (except Steffen, but I didn't see that he's have a meaningful number of varsity matches this year). That is not how the brackets were drawn; instead, Sebastian is given a position that implies a seed lower than all but one unattached wrestler, and is in the same quarter bracket as Coleman. Also in 23.2a is this guideline Stotts was assigned the 16 seed position in the bracket. It is possible, but extremely unlikely, that Stotts would have been placed here by random draw; that is, a random draw that seeds all wrestlers equally, including the 7 imaginary placeholder wrestlers. We could also interpret the bracket, in light of this guideline, as that Stott was determined to have ability below that of an imaginary placeholder wrestler - that is, the imaginary wrestlers were randomly assigned to seeds 9-15. If all the wresters were rated of equal ability and seeds randomly assigned, we would expect that some of the 7 imaginary placeholder wrestlers were assigned seeds 1-8; that didn't happen. We might accept that unattached wrestlers should be consider of higher ability than unattached, at least for the purposes of seeding, then we consider the next guideline This, I think, would have place Steffen and Sebastian in the same quarter bracket, and it would have been Steffen, perhaps, that got the benefit of Sebastians Inj default. We should note that the next guideline is not as vague Clearly, non of these criteria were used to seed this bracket. Finally, I'll repeat a rule quoted earlier This rule follows the rules for seeding, and it should be understood, I think, that the preferred method of assigning byes follows from the guidelines for seeding wrestlers. The alternate method that was used for this tournament failed to distribute byes randomly, by any definition of random that I'm aware.
  4. If I'm reading the bracket correctly, Schoon from SDSU had a bye in the first round, then met Broderson from ISU in the second round. The result is listed as Schoon Inj 0:00. Schoon did lose by decision in the third round to Battani from ISU; Battani then lost to Coleman by Inj 0:02. Schoon, on the back side, wrestled team mate Orris, who had advanced in the consolations with a MFF from Sebastian of Wisc. He then lost to Steffen from Minn in the third place match. Steffen, on his way to third, last to Battani, then received a MFF from Broderson (who advanced on a MFF from Stotts of ISU), then pinned Long of ISU (who entered the consolation round after losing to Coleman by Inj. 0:01. Long then FF to give Orris 5th). All told, it looks like Schoon drove the 4-5 hours to Ames for three matches, going 1-2 and placing 4th in a 9-man bracket. Orris got two matches, went 1-1 for 5th. The SDSU coaches make an effort to get their back-ups matches during the season, I expect they're not particularly happy about this. Battani and Long of ISU both wrestled two matches each, Steffen of Minn wrestled three. I'm counting 6 matches total in a bracket with 9 entrants, with 5 Inj and 3 MFF. The 5 wrestlers who did compete would have been better served to have been given a 5-man round-robin.
  5. Suppose we assume that each weight class is an independent measure of ranking accuracy. How well do the different rankers predict the outcome of a bracket? If we assume that scores are continuous and that errors are randomly distributed, when we can test this using a simple AOV, in R (given that stacked.ching is the long version of the table Ching posted): ching.lm <- lm(Score ~ Source + Weight, data=ching.stacked) anova(ching.lm) ## Analysis of Variance Table ## ## Response: Score ## Df Sum Sq Mean Sq F value Pr(>F) ## Source 8 187.0 23.38 0.7211 0.6722 ## Weight 9 9227.1 1025.23 31.6256 <2e-16 *** ## Residuals 72 2334.1 32.42 ## --- ## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Given that the data sums of scores, we might use a Poisson model, ching.glm <- glm(Score ~ Source + Weight, family=poisson, data=ching.stacked) anova(ching.glm,test="LRT") ## Analysis of Deviance Table ## ## Model: poisson, link: log ## ## Response: Score ## ## Terms added sequentially (first to last) ## ## ## Df Deviance Resid. Df Resid. Dev Pr(>Chi) ## NULL 89 218.387 ## Source 8 3.283 81 215.104 0.9153 ## Weight 9 173.040 72 42.064 <2e-16 *** ## --- ## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 We might continue with a categorical analysis of the table, perhaps Fisher's Exact test (here, the data are in original table form) fisher.test(ching.table,simulate.p.value = TRUE) ## ## Fisher's Exact Test for Count Data with simulated p-value (based ## on 2000 replicates) ## ## data: ching.table ## p-value = 0.9975 ## alternative hypothesis: two.sided Finally, if we don't assume any distribution, a rank-based test is appropriate friedman.test(Score ~ Source | Weight, data=ching.stacked) ## ## Friedman rank sum test ## ## data: Score and Source and Weight ## Friedman chi-squared = 3.4866, df = 8, p-value = 0.9002 friedman.test(Score ~ Weight | Source, data=ching.stacked) ## ## Friedman rank sum test ## ## data: Score and Weight and Source ## Friedman chi-squared = 56.718, df = 9, p-value = 5.722e-09 Long and short - there is more variation among scores between weight classes than there is variation among the rankers, and the range of differences among rankers is small relative to the error within weight classes. The difference between 544 and 588 is about 4 points per weight class, while high and low totals in any weight class, say 125 (45-65) varies more than that. There may be ways to further decompose the error in the comparisons to distinguish (at least in a statistical sense) among the rankers, but there's not enough information in Ching's table.
  6. The question that springs to mind - is this a function of (a) the university (i.e. the culture of the AD, how is the wrestling program funded and supported relative to other sports?), (b) the coaches specific to the university over that period (does the coach focus more on dual-meet wins or tournament wins?) (c) the conference (does the conference dual meet schedule provide enough information for seeding; is the conference allocation biased?) (d) the athlete base (is the university drawing from a regional pool that underperforms on a national stage?) (e) just dumb luck? Consistent under- or over-performance, relative to seed or other ranking systems, suggests a knowledge gap, and a knowledge gap may be exploited, if the answer is not (e). So, is your data base sufficiently detailed to test (a)-(d) against (e)? That's the part I'm still working on.
  7. Oh, yes, there are a lot of refinements to be made. I just knocked out a crude approximation based on rough placing. There's probably more information hiding in the brackets.
  8. This is a zero-sum measure - for every match where one wrestling performs better than his seed, the other wrestling performs worse than his seed. So, yes, if every person wrestles exactly to their seed, then all measures would be 0. Whether it's harder to gain a positive or a negative - that is more a matter of context. Over all of the wrestlers in a tournament, it balances out - for every wrestler that has a bad tournament, there will be a different wrestler that has a good tournament. That will always happen, and that adds a certain amount of background noise to the analysis. The trickier part is separating, from the noise, whether a coming from a particular school changes the probability of having a good or bad tournament.
  9. My day job includes a lot of statistics and data science, and I've been toying with predictive analytics in wrestling. Specifically, how well do different ranking systems predict performance? So I just happen to have the 2018 tournament data on hand. I've written code to convert seed to expected placement, and then calculate expected team scores from placement. Then, we calculate a difference between expected score and placement score. I don't have the entire set of match results in a useful format, so the expected and actual scores are estimates - they do *not* include bonus points, and average over different routes to placement. That said, the top and bottom 5 teams, by difference between expected score based on seed and expected score based on actual place: HOF +4.17 LH +2.83 NEB +2.63 KENT +1.69 PRIN +1.60 OKST -1.30 PENN -1.44 LEH -2.55 RID -2.75 MIZZ -3.33 This should be read as the average points scored per wrestler. It is a crude measure - I knocked in out over the course of an hour - but it does tend to support the original post.
  10. Seth was a (mostly) no-go for ASU, up until the Sunday morning weigh-in. He felt good Sunday, he wrestled. He tweaked his back mid-week leading up to OSU, the decision to hold him wasn't made until Thursday or Friday - don't hold me to the exact date. My memory of the timeline is that Hahn had Gross wrestling as of the Wed. coaches lunch; announced he wouldn't be wrestling at a Friday evening alumni gathering.
  • Create New...