南京林业大学学报(自然科学版) ›› 2005, Vol. 29 ›› Issue (04): 69-72.doi: 10.3969/j.jssn.1000-2006.2005.04.017

• 研究论文 • 上一篇    下一篇

影响图在非线性回归异方差检验中的应用

解锋昌1,李勇2   

  1. 1. 南京农业大学数学系, 江苏 南京 210095; 2. 东南大学数学系, 江苏 南京 210096
  • 出版日期:2005-08-18 发布日期:2005-08-18

Influence Graph for the Nonlinear Regression with Heteroscedasticity

XIE Feng-chang1, LI Yong2   

  1. 1. Department of Mathematics Nanjing Agricultural University, Nanjing 210095, China; 2. Department of Mathematics Southeast University, Nanjing 210096, China
  • Online:2005-08-18 Published:2005-08-18

摘要: <正>采用气一质联用仪对云南梁河的思茅松松脂及松节油进行组成成分分析。发现其含较高3一蒈烯,其林分松脂的3蒈烯含量为8.2%~10.0%,平均值为9.1%(n=4);3-蒈烯在单萜十倍半萜中的质量分数为17.5%~27.9%,平均值为21.7%。单株松脂3蒈烯含量最大值为21.1%,高于高山松6%,单株中3一蒈烯在单萜+倍半萜中质量分数为45.2%(1一12)。实验室甘油法蒸馏所得松节油中3-蒈烯含量为27.0%~30.0%,与松脂中3-蒈烯在单萜+倍半萜中的质量分数相近。

Abstract: In ordinary regression analysis, the homoscedasticity of random error is a basic assumption. But the rationality of these assumptions for variance is doubtable. This paper takes the weighted nonlinear regression model as a perturbed version of a homoscedastic regression model and develops the tests for heteroscedasticity based on normal curvature of its influence graph. Based on this fact,the modified score statistic was discussed in detail. Final-[y these new statistics was applied to two concrete numerical examples.

中图分类号: