Acta mathematica scientia,Series A

• Articles • Previous Articles     Next Articles

Testing for Varying Dispersion in Exponential Family Nonlinear Models with Random Coefficients

 LIN Jin-Guan, WUIBo-Cheng   

  1. 东南大学数学系 南京 210096 江苏教育学院数学系 南京 210013
  • Online:2003-10-25 Published:2003-10-25
  • Supported by:

    国家社会科学基金(02BTJ001)和东南大学博士后基金资助项目

Abstract:

Exponential family nonlinear models with random coeff icients are the extension of models studied by Smith & Heitjan (1993) and Wei et al (1998). This paper dea ls with this type of models and discusses the tests of varying dispersion for constant and nonconstan t weights of dispersion respectively. Several score  test  statistics are obtain ed . European rabbit data (Ratkowsky (1983) are presented for normal, Γand inverse aussian nonlinear models respecti vely to illustrate the methodology.

Key words: Exponential family distribution, Nonlinear models, Random coefficients, Varying dispersion;Score function, Score , test , statistics.

CLC Number: 

  • 62J02
Trendmd