论文信息 - Fitting parametric link functions in generalised linear models

Fitting parametric link functions in generalised linear models

Abstract In a generalised linear model the mean of each observation is assumed to be related to its linear predictor by a known link function. In some cases this link function may not be known exactly, but can be assumed to be of some general ‘parametric’ form. We show how generalised linear models can be extended to fit models with such link functions. Examples given include the two-parameter logistic and estimating the exponent of the Box-Cox link. GLIM-3 coding is supplied.

[1] John Hinde,et al. Compound Poisson Regression Models , 1982 .

[2] Murray Aitkin,et al. Direct Likelihood Inference , 1982 .

[3] A. F. Bissell,et al. A negative binomial model with varying element sizes , 1972 .

[4] A. Scallan,et al. Some Aspects of Parametric Link Functions , 1982 .

[5] Murray Aitkin,et al. The Fitting of Exponential, Weibull and Extreme Value Distributions to Complex Censored Survival Data using GLIM , 1980 .

[6] P. McCullagh,et al. Generalized Linear Models , 1972, Predictive Analytics.

[7] D. Pregibon. Goodness of Link Tests for Generalized Linear Models , 1980 .

[8] F. Richards. A Method of Maximum‐Likelihood Estimation , 1961 .

[9] Robin Thompson,et al. Composite Link Functions in Generalized Linear Models , 1981 .