頁籤選單縮合
題 名 | Removing An Extraneous Effect in Measuring Correlation Coefficient |
---|---|
作 者 | Fu, Chong-yau; Tsai, Min-hsun; | 書刊名 | 中國統計學報 |
卷 期 | 45:4 2007.12[民96.12] |
頁 次 | 頁386-401 |
分類號 | 319.5 |
關鍵詞 | Pearson correlation coefficient; Partial correlation coefficient; Corrected correlation coefficient; Deviated value; Stratification; Regression fitted; |
語 文 | 英文(English) |
英文摘要 | Pearson correlation coefficient is a measure for the linearity degree between two continuous variables (X, Y). When this measure is spurious from an extraneous variable effect (Z), the partial correlation coefficient is often referred to adjust. However, it is possible to obtain a biased result from only the linear effect removed in the partial correlation coefficient applied. This study combines the techniques of “stratification” and “regression fitting” to replace the deviated value of the formula in the Pearson correlation coefficient. The rPR, rGM and rGR are proposed and investigated through simulation technique. And, the results show that rGR , rPR perform very well in simulation I, and rGR still performs very well in simulation II. Meanwhile, in a fetal study, the linear association between femur length and weight is estimated to be about 0.5 (rpR, rGR ),instead of 0.91 (uncorrected Pearson correlation coefficient) ,which is masked from a strong linear association with gestational age. Therefore, rGR is the most reliable estimation and rPR provides a possible method for more than one extraneous variable adjusted. Also, noted that the performance of rPR varies with two data structure (simulation I & II). |
本系統中英文摘要資訊取自各篇刊載內容。