|
|
1 |
Thx for the answers.
|
|
|
2 |
\n
|
| 1 |
The answer to 1. seems to be ideal.
|
3 |
The answer to 1. seems to be ideal.
|
| 2 |
\n
|
4 |
\n
|
| 3 |
And by series of 1 vs everyone you mean the sum over all other teams of 1 vs other team? If yes, 2. is what I would think is ideal, too.
|
5 |
And by series of 1 vs everyone you mean the sum over all other teams of 1 vs other team? If yes, 2. is what I would think is ideal, too.
|
| 4 |
\n
|
6 |
\n
|
| 5 |
For visible deviation, I think the standard deviation should be used instead of variance, the square root of the covariance matrix' diagonal elements. The expected deviation of a players skill is assumed to increase as in a random walk, proportional to sqrt(time). But if variance is used, it is proportional to time.
|
7 |
For visible deviation, I think the standard deviation should be used instead of variance, the square root of the covariance matrix' diagonal elements. The expected deviation of a players skill is assumed to increase as in a random walk, proportional to sqrt(time). But if variance is used, it is proportional to time.
|
| 6 |
\n
|
8 |
\n
|
| 7 |
sqrt(35*time/day) seems a bit much. Did you test that this yields better results than the standard sqrt(14*time/day)?
|
9 |
sqrt(35*time/day) seems a bit much. Did you test that this yields better results than the standard sqrt(14*time/day)?
|
WHR Teams, FFA and Variance