Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
Drexel University or The Math Forum.
|
|
Luis A. Afonso
Posts:
4,277
From:
LIsbon (Portugal)
Registered:
2/16/05
|
|
Re: An experiment . . . at random in intra-Permutations
Posted:
Mar 2, 2013 6:15 PM
|
|
Follow-up
And about the *classical* Bootstrap, what just happens?
Results
Permutations
___________Exp.I__Exp.II_Exp.III__
__n=20_____.984___.992___.989__
____25_____.991___.983___.990__
____30_____.988___.984___.987__
____35_____.990___.993___.990__
____40_____.990___.994___.992______total=14.837
Bootstrap
__n=20_____.985___.984___.980__
____25_____.990___.979___.993__
____30_____.990___.994___.988__
____35_____.992___.994___.989__
____40_____.993___.990___.995______total=14.836
No difference between the two algorithms, the advantage of Bootstrap is that is faster, however Permutations is more convincing because do not admit a item be present in each pseudo-sample more than one time: the complete permutable propriety is what´s demanded only.
Luis A. Afonso
|
|
|
|
