Did Mike Rossi (viral marathon dad) cheat his way into Boston?

Rojo IS doing his job--and he's doing it much better than the overpaid hacks at the Today show and other mainstream media outlets who "covered" Mr. Rossi's diatribe against his children's school principal as a feel-good, dad-of-the-year fluff piece.

Disinterested party wrote:

There's a lot of chatter in this thread about the effort to out this guy ruining his kids' lives, and I'd like to

Why can't you do-gooders who are, oh soo, concerned about his children just stop discussing them?

That's one viewpoint and very well said but pretty much best case scenario.

I was on board with the public humiliation at first but I'm not so much now. I know Mike cheated just like I know Lance cheated 12-15 years before he was officially outed but somewhere in the 40 pages the end game for us here is much more than just a confession.

I can't help thinking this is a Twilight Zone episode and despite all the evidence against Mike that he actually did run 3:11 and 100 years from now society will look at this as a case study along with the Salem witch trials.

The trolling on this thread is absolutely horrendous.

Rojo is doing his job, he is acting as a voice for a sport that very few people care about. While this situation is very different than a WMM champ being busted for EPO, any instance of cheating that goes overlooked or brushed to the side will continue the demise of serious long distance running.

he is a cheater wrote:

If you check Mike's starting time, he didn't cross the mat until 7:10:31AM.

This is interesting. He seems to have started 30 seconds or so after everyone who finished around him -- including basically each of the 50 or so people who finished after him. So he would have had to pass all of these people at some point. And 30 seconds is quite a bit of time to spot someone who's going to run 26.2 at exactly your pace, so he only would've passed them later in the race.

Seems like someone would remember this. My last marathon was three years ago, and I still remember when and who passed me in the last 6 or 8 miles.

He's a journalist and his job and responsibility is to get to the bottom of a developing story. I've written to the TODAY show requesting they follow up on their previous sound bite moral hero story.

Yes, we should all be obsessed with honesty. As a former Marine Corps drill instructor always told us, "At the end of the day, all you have is your word." One important aspect of running and racing is that you can't hide from your fitness level, it's a very honest sport. You know when you're too slow and you know when you're getting better. A lot of hard work goes into improving a tiny bit.. losing that tiny bit is super easy. You're hounding the wrong people about being obsessive.

You're comparing legitimate questions about the plausibility of his Boston qualifier race to the Salem Witch Trials? Really?

BTW--were you on board with the "public humiliation" he caused his children's principal with his self-righteous, totally unjustified social media rant?

It seems that most of Mike's defenders on this forum are mostly ignoring the arguments and trying to deflect attention away from the evidence rather than engaging with it. Honestly, that's probably their best bet. However, to try to keep things focused, I'm going to bring up a new perspective - statistics - on one of our earliest and most important pieces of evidence: the lack of photographs.

You all remember that Rojo created this spreadsheet to distribute the work of looking through the photos along the course:

https://goo.gl/krbo5s

. Well, an army of letsrunners (among whom I'm proud to count myself) sifted through the photos of the 50 runners who finished in front of Mr. Rossi, and the 50 runners who finished after him, to determine at how many locations on the course each runner was seen. As you've surely heard, every one of these runners was seen at least three times on the course (at least two places besides the finish line), while Mr. Rossi was only seen once (only at the finish line).

This is already pretty damning by itself - out of the 100 runners nearest Mr. Rossi, every single one was photographed at at least two intermediate locations, while Mr. Rossi was not photographed at any. It is just common sense that this could not happen by chance.

But we don't need to rely on common sense, which after all can go astray. How strong is this evidence, when it really comes down to it? What are the chances that Mr. Rossi was coincidentally missed by all the photographers, assuming that he really did run the race?

Well, apparently about 1 in 11 thousand.

Let me preface this by saying that I am not an expert on statistics. I'm sure that there are better ways to do this. However, I am confident that what I've done makes sense, and that a more careful analysis would only make things worse for Mr. Rossi. (I hope that someone with more expertise takes it on!) Also, the precise value of this number shouldn't be taken too literally, since it would vary somewhat as we modify our statistical assumptions. (For example, in this case we are assuming that the number of locations follows a normal distribution - an assumption which I actually use further statistics to validate.)

So: I calculated the mean and standard deviation of the "number of different locations on the course where a given runner was seen" for the 100 runners closest to Mr. Rossi. The lowest number of locations was 3, the highest was 7, and the average was 4.66 locations. The standard deviation was 0.97 locations.

I then performed a z-test, which means I assumed the data were normally distributed, and then computed the probability that Mr. Rossi would only have been pictured at the finish line assuming that he actually ran the race. (See 'statistical analysis' tab of the spreadsheet for more details). The result was about 1 in 11,190.

Now, is the assumption that the data is normally distributed a valid one? Yes. I computed the Pearson's chi-squared test statistic from these data. This means that I counted how many runners had three locations, how many had four, etc, and compared that to how many should have had these numbers assuming that the distribution were normal. Then I computed the probability that the data would look as normal as it did, or less normal, assuming that it actually was normal. The answer is 80%, a strong indication that the data is normal, or least very close to it.

(More technically, I found that the pearson's chi-squared = 2.34, then integrated the probability density for the chi-squared distribution with 5 degrees of freedom starting at this value. Five degrees of freedom because there are seven frequencies that we are comparing, and because the model we are comparing two has two estimated parameters (mean and standard deviation). We obtain P(chi^2 > 2.34) = 0.8, from

https://www.fourmilab.ch/rpkp/experiments/analysis/chiCalc.html

. To recap, this means there is an 80% chance that if the # of locations were normally distributed, we'd get a value of chi^2 at least as high as we did.)

So, in summary, that chance that Mike would simply get unlucky enough to miss all the pictures at intermediate locations is less than 1 in 10 thousand.

Speaking about the back to back thing... Did he not also allegedly run 8 - 5k PRs in a row as well??

Madness wrote:

This is just obsessive. Don't you have things to do with your life? A hobby?

And your excuse for being here ?

While you are at it why not be consistent and apply this reasoning to everything you read anywhere ?

Because of PED use, people now doubt the legitimacy of world records and people's PR's.

Do we want cheating to qualify for Boston to become so commonplace and unchallenged that our legitimate BQ's are doubted by the people around us?

Rid the sport of PED users and BQ cheaters.

If anything, these stats understate the case for two reasons. First, if we painstakingly went through the lost and found pics for each person, like we've done for Mike and a few others, we'd certainly find more pics for a bunch of people. (The fact that we've done this for Mike, but not for most other people, is what makes the estimate conservative.) This would not only raise the average number of locations the other runners are seen at, which would strengthen the case against Mike, but more importantly this would also probably lower the standard deviation (since runners with fewer pics are more likely to have more in the lost and found...except for Mike, apparently). However, going through the lost and found pics for everyone would be a lot of work, and in my opinion these stats are damning enough already.

Second, less importantly, the assumption that the number of locations is normally distributed is probably a conservative assumption. A categorical analysis where we kept track of whether pics were taken at each possible location would probably be even more damning. Basically, this would mean counting what fraction of people get captured at each location and figuring out the chances Mike was missed at ALL locations. This would really be the best way to do this, I think, but counting the fraction of people captured at each location sound really hard - unless someone has a way to do this?

Joey Br. wrote:

If Mike really did run a 3:11 marathon then it means on that one day he:

set two half marathon PRs, back-to-back

set four 10K PRs, back-to-back-to-back-to-back

^^^^^

Rojo, write that down!

Good stuff mileage_man. Now add in the outlier performance (faster than 10k PR pace for a marathon) AND the curious lack of detail provided after the race in various social media forms that this character seems to love.

Ridiculous.

So, in summary: The probability that Mr. Rossi would have no pictures taken of him during the race, given the distribution of "# of locations seen" for everyone else, is less than 1 in ten thousand. This assumes that the data is normally distributed, but Pearson's chi-squared test supports that this is a good assumption. This estimate is also conservative (i.e., the true probability is probably even lower) because it ignores the fact that many of these people probably have pics in the lost and found section, while Mr. Rossi does not.

One possible refinement would be to perform a categorical analysis. Better statistical expertise invited!

I think making a statistical case is actually being too kind to him. Statistics should mostly be applied in situations in which the range of outcomes is actually possible. For example, flipping a coin can only yield heads or tails, so you will only be able to predict the probability of heads or tales, not some other face that doesn't exist on the coin. A 3:11 for Mike is not a possibility so I wouldn't even consider it part of the range of outcomes. The DNA passport looks for measures which would fall out of the range of outcomes for each athlete. In my mind we're dealing with something similar here. I wouldn't be that kind to him to offer statistical reasoning since it leads to the illusion that his 3:11 would be possible. It's not possible for him.

Somewhere in those picture archives we're going to see our man in the background, either standing with spectators or caught with hi pants down.

Your 1 in 11,000 is calculated using the 100 runners in proximity to his time. I bet if you did this for all finishers in the race, the 11K number would be a lot higher.

this.

"caught with his pants down" lol

Previous posters have tried to use statistics to estimate the chances he could run a 3:11, and I agree with you that a simple z-test would not be an accurate model in this case, for reasons that you point towards. (Although that analysis does help illustrate what an outlier this time would be, I wouldn't take the probabilities that come from that analysis very seriously. That is, I agree with Unsatisfied that they shouldn't be interpreted as a probability that he could run that time.)

However, just to be clear, what I am doing is totally different. I am asking what the probability is that Mr. Rossi was unlucky enough to get missed by all the photographers, assuming he actually ran the race. (In this case the normality assumption is warranted, as I do further analysis to show.) The answer is about 1 in 11 thousand.