| View previous topic :: View next topic |
| Author |
Message |
J. S. Mill
Maniac Member
Joined: 28 Apr 2003
Location: New York, New York |
20.  Posted: Mon Jun 19, 2006 8:33 pm Post subject: |
 |
|
| Irish.sacred wrote: | | As a total math junky this is definitely intriguing work. Assuming I have any decent amount of free time I'll try to get in touch with you about some of this stuff - or feel free to IM me if you want to just talk about any data you think you might want to collect or anything I could do to help or whatever. |
Thanks, I'll do that. I'm working right now on a long essay regarding this work, so I'll communicate with you about it.
| nasheq wrote: | | i think the entire 96% prediction accuracy is bullshit. |
I show the statistics in the essay. With what basis do you make this remark?
| nasheq wrote: | | also i'm sure you aren't claiming that you will predict future matches |
Yes, I am, and yes, I have.
_________________
|
|
| Back to top |
|
 |
Emptyeye
Trick Member
Joined: 28 Jan 2006
Location: Waterbury, CT |
| 21. Posted: Fri Jun 23, 2006 2:16 pm Post subject: |
|
|
A bit of a bump, but oh well, please don't kill me. 
| John Locke wrote: |
Well, you have the essence of the distinction correct. But the specifics might be a bit off. |
Probably. In hindsight, my V^2 example was probably a poor one to illustrate what I was trying to get at, which was--and let me see if I remember the terminology from the AP Statistics class five years ago--that there is not necessarily a strong positive correlation between Integrated Difficulty and Tournament Difficulty. It may turn out that such a correlation does indeed exist--you have the data, not me--but my point was that this was not automatically the case like some may expect.
| John Locke wrote: |
A good example would be to compare Disconnected Hyper with Visible Noise. Hyper has a higher Integrated Difficulty (it's just a harder song), but Visible Noise has a higher Tournament Difficulty (since it factors in the difficulty of staying consistent on the song).
[...]
When calculating the efficiency of songs, we inverse the range factor (which measures the difficulty in staying consistent on a song). So, in fact, you are looking for songs with high Integrated Difficulties but with (relatively) lower marginal Tournament Difficulties. |
So using the D/C Hyper vs. Visible Noise example, if Joe Average decides he'd like to enter a tourney, of those two songs, it would be to his advantage to get D/C Hyper down cold, since it has the higher Integrated Difficulty but the lower Tournament Difficulty, which is what we're looking for, correct?
| John Locke wrote: | | As for your final question, I meant the former (worthless because only tournaments determine the best). |
I guessed as much.
Like Irish.sacred, I'm definitely interested in this stuff, though my capacity to help is sadly limited. Still, if there's something you want to discuss or whatever, feel free to E-mail or IM me (Yes, the AIM name is real, though I'm not on particularly often) and I'll do what I can.
Final question: I presume the essay will also show the source of statistics like "Tournament Efficiency" you've talked about on ITGFreak? That stat in particular is one I'm curious about.
@nasheq: Don't forget, while there will be the fair share of Lil Q vs. Unknown matches (Replace "Lil Q" with any world-class player of your choosing), he'll also have a high concentration of two elite players going against one another (Particularly if he's working from a dataset similar to what I think he is), as well as, probably, an even higher concentration of Unknown #1 vs. Unknown #2 to work with.
_________________
|
|
| Back to top |
|
|
|
|
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
|
Powered by phpBB 2 © 2001, 2002 phpBB Group
|
Forums FAQ
Search
Memberlist
Usergroups
Register
Profile
Login to check your private messages
Login
