No statistically significant improvement in marathon results since Vaporfly introduction

you didn't preform a statistical test. nice work, but there's a bit more to be done to reach your conclusion.

cheers.

Try running in a pair and you will say there is a significant improvement.

I've run in Vaprofly 4% model and I haven't seen significant improvement in my results though I don't deny that these shoes are masterpiece of shoe engineering. But not because they'd improve my results but because they save my legs. Much less stiffness after hard workouts and races and faster recovery.

I've also discussed this subject with few 64-65 min half marathoners and they haven't seen significant improvement in their racing times. They have PRed but the improvements have been in line with their general year-to-year progress of about 20-30 sec per year.

Dril wrote:

you didn't preform a statistical test. nice work, but there's a bit more to be done to reach your conclusion.

cheers.

Agreed. And you know 2019 isn't over yet right? In 2014, only 174 of the 196 marathons were run between January and October. So 2019 is on pace to be a record year with 180 so far.

You are not even using the term "sample size" correctly. Your sample size is 12 years. Based on your own reasoning that is too small.

This must be a troll post, because it is a wholly inappropriate and inadequate measure of vaporfly vs. non-vaporfly. This shows absolutely nothing.

How do you know whom of those sub-2:10 did use vaporfly and whom did not ?

dude really wrote:

Try running in a pair and you will say there is a significant improvement.

Some tracks are extra bouncy relative to other tracks and make you feel and run faster. Why don't we ban tracks altogether if they can't all be the same?

NotCorrect wrote:

How do you know whom of those sub-2:10 did use vaporfly and whom did not ?

It would not matter if we knew who wore the shoes.

In 2014 and 2013 and 2012 etc nobody had the shoes.

So, once the shoes were introduced, there should have been a marked increase in sub 2:10s, because a lot of runner use Nikes.

7 of the top 10 marathon performances of all time have been run in Vaporflies.

You’re really smart

No, sample size is correct, it's all 2921 results in history to date. I just posted statistics for the last decade or so but the distribution is correctly calculated. Here is full list of the same sample. It's actually interesting that 2008 have been a significant turning point, much more impactful than VF introduction with sudden significant increase in sub-2:10 performances.

2019 – 180 (6.1%)

2018 – 171 (5.9%)

2017 – 186 (6.4%)

2016 – 146 (5.0%)

-----------------------

2015 – 167 (5.7%)

2014 – 196 (6.7%)

2013 – 173 (5.9%)

2012 – 197 (6.7%)

2011 – 174 (6.0%)

2010 – 158 (5.4%)

2009 – 116 (4.0%)

2008 – 106 (3.6%)

2007 – 79 (2.7%)

2006 – 64 (2.2%)

2005 – 65 (2.2%)

2004 – 66 (2.3%)

2003 – 99 (3.4%)

2002 – 70 (2.4%)

2001 – 45 (1.5%)

2000 – 59 (2.0%)

1999 – 64

1998 – 58

1997 – 55

1996 – 22

1995 – 17

1994 – 28

1993 – 7

1992 – 11

1991 – 7

1990 – 10

1989 – 14

1988 – 20

1987 – 2

1986 – 16

1985 – 18

1984 – 10

1983 – 21

1982 – 7

1981 – 5

1980 – 4

1979 – 1

1978 – 1

1977 – 0

1976 – 1

1975 – 1

1974 – 1

1973 – 0

1972 – 0

1971 – 0

1970 – 1

1969 – 1

1968 – 0

1967 – 1

Care to take time to provide valid argument? We know that VF was introduced in 2016 but during last four years we haven't seen significant improvement in results over previous four year cycle or even pre-previous four year cycle. If Vaporfly shoes were truly giving major advantage we would see an increase in results similary like something around 2008.

No need to know, because no changes in distribution can be seen.

Correlation does not imply causation

5 of the top 10 marathon per formances were run either by Kipchoge or Bekele.

7 of the top 10 marathon performances were run in Berlin or Boston.

10 of the top 10 marathon performances were run either by Kenyan or Ethiopian.

So the looks like Adidas adios release dates had just as big statistical impact on sub 2:10 as the Nike vaporfly just the vaporfly. Just with the vaporfly being my economical than the adios and light the times decreased.

Or the it could just be the influx of elites attempting the marathon as it’s becoming trendy to do it again and not focus on track

Show the numbers from 2008 onwards for sub 2:09, sub 2:08, sub 2:07 etc and see how that compares.

I'll do that later but the sample size decreases exponentially with each minute taken off from result which means a single fast race in good conditions can distort distribution by as much as 5%. I choose sub-2:10 as this was the most of data I could aquire.

Who knows when Adios were introduced? Was it really 2008?

I think a problem with this is that in 2016, not many runners had access to Vaporflys.

If you just looked at 2017-2019 (all of it) compared to the three years before you would get a different result. >= 18.4% vs 17.4%.

Mostly, I think this shows that the method is not solid.

sbeefyk2 wrote:

Some tracks are extra bouncy relative to other tracks and make you feel and run faster.

Since when does a bouncy track make you faster? Does it bounce you forward, or up? Where's the advantage in prolonging footstrike and lowering cadence?

Does bouncing save you energy? If the ground beneath you accelerates upward, exerting a greater force on your foot, do you not have to counter that with an equal and opposite greater force?

2016 wrote:

I think a problem with this is that in 2016, not many runners had access to Vaporflys.

If you just looked at 2017-2019 (all of it) compared to the three years before you would get a different result. >= 18.4% vs 17.4%.

Why is method not solid? Because you don't see what you would like to see?

Let's take three other successive years before VF era began:

2013,14,15 = 536 (18.3%)

2012,13,14 = 566 (19.3%)

2011,12,13 = 544 (18.6%)

2010,11,12 = 529 (18.1%)

If Vaporfly shoes gave 2% boost in performance they'd make 2:10:01-2:12:30 marathoners a sub-2:10 runners instantly. Everyone that is familiar with Gaussian (normal) distribution understands that this would give significant increase in sub-2:10 performances due to nature of exponentially more runners being able to yield such performance.

It's because many athletes retired at the time of the Vaporfly introduction, because they felt they gave an unfair advantage. Had those people been less ethical, the amount of sub 2:10s would have increased by a lot.