| タイトル | Linear Least Squares for Correlated Data |
| 本文（外部サイト） | http://hdl.handle.net/2060/20040112005 |
| 著者（英） | Dean, Edwin B. |
| 著者所属（英） | NASA Langley Research Center |
| 発行日 | 1988-01-01 |
| 言語 | eng |
| 内容記述 | Throughout the literature authors have consistently discussed the suspicion that regression results were less than satisfactory when the independent variables were correlated. Camm, Gulledge, and Womer, and Womer and Marcotte provide excellent applied examples of these concerns. Many authors have obtained partial solutions for this problem as discussed by Womer and Marcotte and Wonnacott and Wonnacott, which result in generalized least squares algorithms to solve restrictive cases. This paper presents a simple but relatively general multivariate method for obtaining linear least squares coefficients which are free of the statistical distortion created by correlated independent variables. |
| NASA分類 | Statistics and Probability |
| 権利 | No Copyright |
| URI | https://repository.exst.jaxa.jp/dspace/handle/a-is/87974 |
