$20.00
$15.00
$5.00
Greysbull
United States
Greeley
Colorado
flag msg tools
mbmbmbmbmb
I really thought I understood how the BGG ranking worked. I guess I was wrong. How can a game with almost 200 fewer ratings and an average rating of 8.64 show up above a game with average rating of 9.12? sauron

 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Nerds call me
United States
N Denver
Colorado
flag msg tools
mbmbmbmbmb
I believe they scale the rankings based on the year the users put them in. So if someone put a 10 in for KDM in 2013 and haven't changed it, then it takes a lower priority to a 2016 ranking of a 10.

Or something, the BGG rankings are useless.
4 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Greg S
United States
Gloucester
Massachusetts
flag msg tools
mbmbmbmbmb
There is a time, or velocity, component to the rankings. And probably some other fuzzy components, beyond just number of votes and average vote.
1 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Sid Rain
United States
Columbus
Ohio
flag msg tools
mbmbmbmb
Aren't these all just arbitrary, meaningless numbers anyways? I mean, if you look at Hamburgum, it obviously deserves a place in the top 100 games, but yet BGG has it ranked as #540 (as of 11/14 11:55am EST). This is clearly a travesty and evidence that BGG's ranking system is horribly broken.
1 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
ArtSchool
Spain
flag msg tools
mbmbmbmbmb
So it all boils to: YES, you need one (probably not worth bothering anyway XD)

1 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Greysbull
United States
Greeley
Colorado
flag msg tools
mbmbmbmbmb
Thanks for the replies, guys. So, it looks like that at the end of the day, the current ranking system kind of enables the dreaded "cult of the new" everybody complains about...
2 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
L S
Germany
flag msg tools
mbmbmbmbmb
According to the FAQ (https://boardgamegeek.com/wiki/page/BoardGameGeek_FAQ), the BGG ranking system employs some sort of "Bayesian averaging" to prevent games with few votes to top the overall ratings. The constant used for the Bayesian average depends on the variation in the dataset, which indicates the degree to which users are in agreement or disagreement about a game's quality, i.e. the objectivity/reliability of the user scores. Since user ratings for MvM have a standard deviation of 1.26 compared to KDM's 1.73, the former is adjusted towards the theoretical average of 5.5 less strongly than the latter.
8 
 Thumb up
5.00
 tip
 Hide
  • [+] Dice rolls
Nathan Ehlers
United States
Cleveland
Ohio
flag msg tools
I love you!
badge
mbmbmbmbmb
Randombias wrote:
According to the FAQ (https://boardgamegeek.com/wiki/page/BoardGameGeek_FAQ), the BGG ranking system employs some sort of "Bayesian averaging" to prevent games with few votes to top the overall ratings. The constant used for the Bayesian average depends on the variation in the dataset, which indicates the degree to which users are in agreement or disagreement about a game's quality, i.e. the objectivity/reliability of the user scores. Since user ratings for MvM have a standard deviation of 1.26 compared to KDM's 1.73, the former is adjusted towards the theoretical average of 5.5 less strongly than the latter.


Thank you! Have some .
2 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Robert Ell
United States
Seattle
Washington
flag msg tools
mb
Like many other things on BGG, it's a long history of quick fixes never actually implemented properly. At some point, they decided that hot games getting high ratings due to their newness didn't deserve to climb to the top of the ratings. So they hacked something in, and here we are.
1 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Didier Renard
France
Saint-Louis
flag msg tools
mbmbmbmbmb
Yes it might help!
(answering the thread question...)
 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Lonny x
msg tools
mbmbmbmb
Randombias wrote:
According to the FAQ (https://boardgamegeek.com/wiki/page/BoardGameGeek_FAQ), the BGG ranking system employs some sort of "Bayesian averaging" to prevent games with few votes to top the overall ratings. The constant used for the Bayesian average depends on the variation in the dataset, which indicates the degree to which users are in agreement or disagreement about a game's quality, i.e. the objectivity/reliability of the user scores. Since user ratings for MvM have a standard deviation of 1.26 compared to KDM's 1.73, the former is adjusted towards the theoretical average of 5.5 less strongly than the latter.


Get rid of this...According to the FAQ add this... Elementary, My Dear Watson...bam post of the year
2 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Greysbull
United States
Greeley
Colorado
flag msg tools
mbmbmbmbmb
Well, what else to expect from a guy called RandomBias on a thread about statistics?
2 
 Thumb up
 tip
 Hide
  • [+] Dice rolls
Front Page | Welcome | Contact | Privacy Policy | Terms of Service | Advertise | Support BGG | Feeds RSS
Geekdo, BoardGameGeek, the Geekdo logo, and the BoardGameGeek logo are trademarks of BoardGameGeek, LLC.