Tournament AGPL III - Commencement Thread

cromagnet

cromagnet

I pledge allegiance to the grind
is a Forum Moderator Alumnusis a Community Contributor Alumnusis a Battle Simulator Staff Alumnus
So one day bored I figured I would use basic statistics to get a feel of how much each player would go for in the draft. So I spent a few hours compiling data from each of the 11 mocks to find out

Can mock drafts be used to predict a player's price in the real auction?
​
Methods.
I took each player's price in each mock that they were drafted in and compiled the average and 95% confidence interval, which gave me an appropriate estimate of how much a player should go for in the draft if the managers for real played like the managers in the mock. This is also why I didn't participate in these mocks, as I did not want to alter the data since I was doing this. I use the number of drafts a player was chosen in as the sample size to base the projected price interval for that player.

Results.
1624739847049.png

1624739876980.png
Confidence intervals are at the 95% confidence interval. Red represents an inaccurate projection and green represents an accurate projection. The projected intervals are not in multiples of 500 like the draft due to the nature of the calculations. N/A represents the interval of a player only drafted in 1 mock since no interval can be calculated.

Interpretation and Conclusions.
From the data above, out of 56 players drafted (managers don't count and Leru & 64 Squares) were not involved in any mocks), 26 (46%) were correctly predicted, 24 (43%) were drafted for less than predicted, and 6 (11%) were drafted for more than predicted. So it does not seem that mock drafts are an accurate indicator of a player's real price. However, mock drafts can still be used as a good gauge for managers to base their draft plans on as 89% of players went for equal or less than their expected price!
There are inherent issues with this method. All 11 mock drafts were included in the data so the players available to draft do not reflect the pool at the end (i.e. Dockiva withdrawing, pichus joining late).
Overall, some very interesting data, AG is unique in that there is a mock draft nearly every day so there was a lot of data to use for this. Hope you all found this as interesting as I did.

Also go crobats!
1624740485859.png
 
Last edited:

Unicorns

Banned deucer.
cromagnet said:
So one day bored I figured I would use basic statistics to get a feel of how much each player would go for in the draft. So I spent a few hours compiling data from each of the 11 mocks to find out

Can mock drafts be used to predict a player's price in the real auction?
​
Methods.
I took each player's price in each mock that they were drafted in and compiled the average and 95% confidence interval, which gave me an appropriate estimate of how much a player should go for in the draft if the managers for real played like the managers in the mock. This is also why I didn't participate in these mocks, as I did not want to alter the data since I was doing this. I use the number of drafts a player was chosen in as the sample size to base the projected price interval for that player.

Results.
Confidence intervals are at the 95% confidence interval. Red represents an inaccurate projection and green represents an accurate projection. The projected intervals are not in multiples of 500 like the draft due to the nature of the calculations. N/A represents the interval of a player only drafted in 1 mock since no interval can be calculated.

Interpretation and Conclusions.
From the data above, out of 56 players drafted (managers don't count and Leru, 64 Squares, and MAMP were not involved in any mocks), 26 (46%) were correctly predicted, 24 (43%) were drafted for less than predicted, and 6 (11%) were drafted for more than predicted. So it does not seem that mock drafts are an accurate indicator of a player's real price. However, mock drafts can still be used as a good gauge for managers to base their draft plans on as 89% of players went for equal or less than their expected price!
There are inherent issues with this method. All 11 mock drafts were included in the data so the players available to draft do not reflect the pool at the end (i.e. Dockiva withdrawing, pichus joining late).
Overall, some very interesting data, AG is unique in that there is a mock draft nearly every day so there was a lot of data to use for this. Hope you all found this as interesting as I did.

Also go crobats! View attachment 352711
Click to expand...
That's a lot of words to say

Tl;dr: Cromagnet = nerd and Lycanrocs are going to win!
 

Crunchman

Banned deucer.
cromagnet said:
So one day bored I figured I would use basic statistics to get a feel of how much each player would go for in the draft. So I spent a few hours compiling data from each of the 11 mocks to find out

Can mock drafts be used to predict a player's price in the real auction?
​
Methods.
I took each player's price in each mock that they were drafted in and compiled the average and 95% confidence interval, which gave me an appropriate estimate of how much a player should go for in the draft if the managers for real played like the managers in the mock. This is also why I didn't participate in these mocks, as I did not want to alter the data since I was doing this. I use the number of drafts a player was chosen in as the sample size to base the projected price interval for that player.

Results.
Confidence intervals are at the 95% confidence interval. Red represents an inaccurate projection and green represents an accurate projection. The projected intervals are not in multiples of 500 like the draft due to the nature of the calculations. N/A represents the interval of a player only drafted in 1 mock since no interval can be calculated.

Interpretation and Conclusions.
From the data above, out of 56 players drafted (managers don't count and Leru & 64 Squares) were not involved in any mocks), 26 (46%) were correctly predicted, 24 (43%) were drafted for less than predicted, and 6 (11%) were drafted for more than predicted. So it does not seem that mock drafts are an accurate indicator of a player's real price. However, mock drafts can still be used as a good gauge for managers to base their draft plans on as 89% of players went for equal or less than their expected price!
There are inherent issues with this method. All 11 mock drafts were included in the data so the players available to draft do not reflect the pool at the end (i.e. Dockiva withdrawing, pichus joining late).
Overall, some very interesting data, AG is unique in that there is a mock draft nearly every day so there was a lot of data to use for this. Hope you all found this as interesting as I did.

Also go crobats! View attachment 352711
Click to expand...
id be interested in seeing data for the people who may have been drafted in mocks (perhaps for more than base) but subsequently were not drafted in the real draft...
 

Garrett

Banned deucer.
cromagnet said:
So one day bored I figured I would use basic statistics to get a feel of how much each player would go for in the draft. So I spent a few hours compiling data from each of the 11 mocks to find out

Can mock drafts be used to predict a player's price in the real auction?
​
Methods.
I took each player's price in each mock that they were drafted in and compiled the average and 95% confidence interval, which gave me an appropriate estimate of how much a player should go for in the draft if the managers for real played like the managers in the mock. This is also why I didn't participate in these mocks, as I did not want to alter the data since I was doing this. I use the number of drafts a player was chosen in as the sample size to base the projected price interval for that player.

Results.
Confidence intervals are at the 95% confidence interval. Red represents an inaccurate projection and green represents an accurate projection. The projected intervals are not in multiples of 500 like the draft due to the nature of the calculations. N/A represents the interval of a player only drafted in 1 mock since no interval can be calculated.

Interpretation and Conclusions.
From the data above, out of 56 players drafted (managers don't count and Leru & 64 Squares) were not involved in any mocks), 26 (46%) were correctly predicted, 24 (43%) were drafted for less than predicted, and 6 (11%) were drafted for more than predicted. So it does not seem that mock drafts are an accurate indicator of a player's real price. However, mock drafts can still be used as a good gauge for managers to base their draft plans on as 89% of players went for equal or less than their expected price!
There are inherent issues with this method. All 11 mock drafts were included in the data so the players available to draft do not reflect the pool at the end (i.e. Dockiva withdrawing, pichus joining late).
Overall, some very interesting data, AG is unique in that there is a mock draft nearly every day so there was a lot of data to use for this. Hope you all found this as interesting as I did.

Also go crobats! View attachment 352711
Click to expand...
Since you have it formatted already, what’s probably most significant is whether, at the 95% level, we can say there’s statistical evidence for whether the number of people above and below their (say, median) mock draft price are different. By the 43% too low, that’s certainly true. This way you’re testing on a larger number of data points and having a safer assumption for a normal distribution

n being 11 at most means most of the bounds of the CIs are really, really conservative (and then some with a lower bound less than 3k). Idk if you used Excel but switching to a t over z distribution for the critical score might be a better estimate, even though neither are super useful when bid prices are not continuous (multiples of 500, so discrete).

If you can pass a file with the raw data I could probably throw it into excel or R.
 
cromagnet

cromagnet

I pledge allegiance to the grind
is a Forum Moderator Alumnusis a Community Contributor Alumnusis a Battle Simulator Staff Alumnus
BasedWhat? said:
Since you have it formatted already, what’s probably most significant is whether, at the 95% level, we can say there’s statistical evidence for whether the number of people above and below their (say, median) mock draft price are different. By the 43% too low, that’s certainly true. This way you’re testing on a larger number of data points and having a safer assumption for a normal distribution

n being 11 at most means most of the bounds of the CIs are really, really conservative (and then some with a lower bound less than 3k). Idk if you used Excel but switching to a t over z distribution for the critical score might be a better estimate, even though neither are super useful when bid prices are not continuous (multiples of 500, so discrete).

If you can pass a file with the raw data I could probably throw it into excel or R.
Click to expand...
oh no hypothesis testing lol I was just using it in the way I do for research which is just assume that if the value falls within 95% CI it isn't statistically significant. I'll send the raw data your way tho.
 
pannu

pannu

MEDKIT CUZ SHES HEALABLE
is a Top Tiering Contributoris a Top Contributoris a Social Media Contributor Alumnus
Predicts

:vivillon: Vicious Vivillon vs Limitless Lycanrocs :lycanroc:

4-3

SS AG: Shivam3299 vs PinkDragonTamer, (30-70) one of the best AG players atm, while shivam is a really good player i think that pdt will simply outplay in the builder aswell as in the actual game
SS AG: Monsareeasy vs jerryl309, (60-40) arctic is not stupid, i cant imagine him losing to whatever cheese jerry brings
SS AG: baconeatinassassin vs lotiasite, (70-30) bacon is simply just one of the best ag players atm, even if he doesn't have the prep time i am certain he can bring something against loti and outplayinto a win
ND AG: Yami vs Kate, (20-80) Kate actually plays this tier and is way more up-to-date with the meta
USUM AG: Jrdn vs velvet, (90-10) Jrdn is good at the game
USUM AG: Andyboy vs Satanic Beast, (90-10) what i said about jrdn applies here too
ORAS AG: MAMP vs chlo (10-90) what i said about jrdn and andy applies here too
BO3 AG: Quantum Tesseract vs WSun1, (50-50) qt is one of the best pilots in the game, meanwhile will is one of the best ag mainers, specifically for his usum and galar performances. I think this game will boil down to whoever can take USUM, as i heavily favour qt in oras and will in galar.




:luvdisc: The Likable Luvdiscs vs Lottery Laprases :lapras:

2-6

SS AG: Ballfire vs Trade, (40-60) ngl i don't really know much about either of these two but I've heard more stuff abt trade
SS AG: TrueNora vs FatFighter2, (55-45) while i think ff2 is the better player between the two nora has more ssag experience, which might give him an edge here
SS AG: LiderMeliodas vs Rotten, (30-70) Rotten is just an incredibly solid player, not much to say here
ND AG: Nevelle vs Staxi, (51-49) Nev is one of the best ndag mainers, but i honestly barely favour him over staxi in this mu since staxi is such an incredible pilot and has the building support of icemaster among others on his side
USUM AG: MZ vs Skarph, (20-80) skarphoat also i think mz might load up usum pu on accident
USUM AG: temp vs 64 Squares, (20-80) something something joke about 64 being salty and temp making a youtube video on it (go sub to temp on yt btw)
ORAS AG: Highlord vs keys (45-55) Keys is very solid at oras ag, having a lot of experience with it, and while i haven't seen highlord play, fardin hypes them up a ton so they must be good
BO3 AG: Zayele vs Icemaster, (45-55) most hype game of the tour, Zayele is probably the best oras player and she has very good building support in the other two generations as well, meanwhile icemaster is one of the strongest ss players, once again i think that this game will also boil down to whoever takes usum, however i think that it will be ice
 
You must log in or register to reply here.

Users Who Are Viewing This Thread (Users: 1, Guests: 0)

  • ... and 1 more.
    • Top