View Single Post
  #8   Spotlight this post!  
Unread 19-04-2015, 02:51
Spoam's Avatar
Spoam Spoam is offline
Registered User
AKA: Pedro M.
FRC #0955 (CV Robotics)
Team Role: Programmer
 
Join Date: Feb 2014
Rookie Year: 2012
Location: Corvallis
Posts: 54
Spoam is a jewel in the roughSpoam is a jewel in the roughSpoam is a jewel in the roughSpoam is a jewel in the rough
Re: 2015 Championship division simulated rankings

Quote:
Originally Posted by MechEng83 View Post
This is awesome!

I do have a suggestion (which also may not convey easily in words) which could be even better, but also requires more input data.

Rather than using a +/- 10 range in OPR, it would be good to use a team's standard deviation of OPR, which I guess would be related to the residuals from the OPR calculation. I don't know if this information is readily available, but it could narrow or expand the range possible, based on a team's consistency.

Just a thought.
I had the exact same idea actually. The problem with the OPR residual, however, is that it gives you information about the accuracy of the regression with regard to each match, not each robot.

If you took the set of residuals from the matches a robot played in, it makes intuitive sense that that data should contain some level of information about that robot's deviation from their OPR. But is a data set of only 8-12 elements enough for this value to dominate the noise generated by their alliance partners' deviations (and therefore produce a meaningful standard deviation itself)? I dunno.

If some statistics wiz would like to chime in on this, I'd love to hear it.
__________________
2015 PNW District Champions (955, 1983, 2930)





Co-Creator of 955 OPR
Reply With Quote