| 作成者 |
|
|
|
| 本文言語 |
|
| 出版者 |
|
|
|
| 発行日 |
|
| 収録物名 |
|
| 巻 |
|
| 号 |
|
| 開始ページ |
|
| 終了ページ |
|
| 出版タイプ |
|
| アクセス権 |
|
| Crossref DOI |
|
| 関連DOI |
|
|
|
| 関連URI |
|
|
|
| 関連情報 |
|
|
|
| 概要 |
This paper is concerned with estimating the correlation dimension from chaotic time series. First, we show in simulation that confidence intervals of correlation dimension constructed by Smith(1992) a...nd Judd(1992) fail to take into account the variability due to the sensitivity to the initial conditions, the characteristic feature of chaos. Next, we propose a new estimator with weighted least squares in the formulation of Cutler(1990). It is shown that the estimator has smaller dependence on scaling region and variance than Cutler's and Smith's estimator.続きを見る
|
Mendeley出力
