| タイトル | Spline methods for approximating quantile functions and generating random samples |
| 本文（外部サイト） | http://hdl.handle.net/2060/19850008256 |
| 著者（英） | Schiess, J. R.; Matthews, C. G. |
| 著者所属（英） | NASA Langley Research Center |
| 発行日 | 1985-01-01 |
| 言語 | eng |
| 内容記述 | Two cubic spline formulations are presented for representing the quantile function (inverse cumulative distribution function) of a random sample of data. Both B-spline and rational spline approximations are compared with analytic representations of the quantile function. It is also shown how these representations can be used to generate random samples for use in simulation studies. Comparisons are made on samples generated from known distributions and a sample of experimental data. The spline representations are more accurate for multimodal and skewed samples and to require much less time to generate samples than the analytic representation. |
| NASA分類 | STATISTICS AND PROBABILITY |
| レポートNO | 85N16565
NASA-TP-2389
L-15850
NAS 1.60:2389 |
| 権利 | No Copyright |
| URI | https://repository.exst.jaxa.jp/dspace/handle/a-is/157425 |
