One standard error rule, classification in Matlab

12 ビュー (過去 30 日間)
Radoslav Vandzura
Radoslav Vandzura 2016 年 2 月 22 日
回答済み: Ilya 2016 年 2 月 23 日
Hello All. I don´t understand this part of documentation of classification in Matlab:
Could you someone explain me, for what reason we use one standard error? What is purpose of it? Is any other documentation which explain it better?
Thank you in advance...
  1 件のコメント
Radoslav Vandzura
Radoslav Vandzura 2016 年 2 月 23 日
Anyone? :(

サインインしてコメントする。

採用された回答

Ilya
Ilya 2016 年 2 月 23 日
The purpose is to simplify the tree without losing too much accuracy. One standard error is a heuristic rule. If one number is within one standard error from the other number, the two numbers can be thought of as statistically equal. The one standard error rule was introduced in the Classification and Regression Trees book by Breiman et al.; you might want to consult the book for more info.

その他の回答 (0 件)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by