Subject:
|
Re: Lego Purity
|
Newsgroups:
|
lugnet.general
|
Date:
|
Tue, 25 Sep 2007 22:35:57 GMT
|
Viewed:
|
4541 times
|
| |
|
|
In lugnet.general, Tim David wrote:
| |
Hmmm, I know I’m not Mr Pure, but I’m not sure why I scored quite so
low!
|
Alright, I sneakily changed how it calculates things behind-the-scenes, so...
you’re still low, but not *AS* low.
Basically, I was using a weighted average and a straightforward “distance from
the mean” method for calculating scoring. I now generate the score 4 different
ways, using:
- weighted average, distance from mean
- unweighted average, distance from mean
- weighted average, standard deviation from mean
- unweighted average, standard deviation from mean
And then I pick the “best” of those scores (IE the one that was closest to what
you rated yourself, since you’re still the best judge), and shows you that one.
Admittedly, that part makes me feel dirty-- rather than just picking an
algorithm that I think predicts best and always using it.
DaveE
|
|
Message has 2 Replies:
 | | Re: Lego Purity
|
| (...) So, then, the way you're fudging the LEGO purity scores... makes you less pure? Wow, this could get needlessly self-referential... (17 years ago, 26-Sep-07, to lugnet.general)
| | | Re: Lego Purity
|
| (...) Are you sure the Pure/Impure headings above the scores are the right way round? According to them, I score 10/10 :D ROSCO (17 years ago, 26-Sep-07, to lugnet.general, FTX)
|
Message is in Reply To:
| | Re: Lego Purity
|
| (...) Hmmm, I know I'm not Mr Pure, but I'm not sure why I scored quite so (URL) low>! Tim (17 years ago, 25-Sep-07, to lugnet.general, FTX)
|
43 Messages in This Thread:
 
  
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
This Message and its Replies on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
