手法を比較
選択した手法を並べて確認できます。異なる行はハイライト表示されます。
| ウィンザ法（Winsorized Estimation）× | 頑健な相関（スピアマン、ケンドール、およびバイウェイト）× | |
|---|---|---|
| 分野 | 統計学 | 統計学 |
| 系統 | Regression model | Regression model |
| 提唱年≠ | 1960 | 2012 |
| 提唱者≠ | Dixon (1960); robust estimation tradition (Wilcox) | Spearman rank, Kendall tau; biweight from Wilcox / Shevlyakov & Oja robust statistics tradition |
| 種類≠ | Robust location/scale estimator | Robust correlation measures |
| 原典≠ | Dixon, W. J. (1960). Simplified Estimation from Censored Normal Samples. Annals of Mathematical Statistics, 31(2), 385-391. DOI ↗ | Wilcox, R. R. (2012). Introduction to Robust Estimation and Hypothesis Testing. Academic Press. ISBN: 978-0123869838 |
| 別名≠ | winsorization, winsorized mean, Winsorize Edilmiş Tahmin | Spearman correlation, Kendall tau, biweight midcorrelation, rank correlation |
| 関連 | 5 | 5 |
| 概要≠ | Winsorized estimation is a robust technique that reduces the influence of outliers by clamping the extreme percentiles of a distribution to a chosen threshold. Introduced by Dixon (1960) and developed in the robust-estimation tradition of Wilcox, it keeps every observation in the sample rather than discarding any. | Robust Correlation is a family of association measures that resist outliers, covering Spearman's rank correlation, Kendall's tau, and the biweight midcorrelation. Drawing on the robust-statistics tradition described by Wilcox (2012) and Shevlyakov & Oja (2016), it measures how strongly two variables move together without being distorted by a few extreme points. |
| ScholarGateデータセット ↗ |
|
|