Summary
In their originaL formulation of a generalised linear model. Neider and Wedderburn assumed a known relation (‘link’) between the mean of each observation and its corresponding linear predictor. It is possible to allow unknown parameters in this link function and Scallan. Gilchrist and Green(1984) discuss a stable 2-stage algorithm for estimating these extra parameters. This paper notes how an extension of the concept of a link. namely the ‘composite’ links of Thompson and Baker (1981). can be further extended by treating them as having unknown parameters. This, for example, allows the fitting of models with a correlated error structure.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
AITKIN, M. (1982). Direct likelihood inference. In GLIM82, ed.
R.Gilchrist, New York: Springer Verlag.
BAKER, R.J., PIERCE, C.B. and PIERCE, J.M. (1980). Wadley’s problem with controls. GLIM Newsletter, Dec, pp. 32–35.
BOX, G.P. and TIDWELL, P.W. (1962). Transformations of the independent variables. Technometrics, No. 4, pp. 531–550.
GREEN, P.J. (1984). Iteratively reweighted least squares for maximum likelihood estimation and some robust and resistant alternatives. J.R.Statist.Soc., B, 46.
JORGENSEN, B. (1983). Maximum likelihood estimation and large sample inference for generalised linear and non-linear regression models. Biometrika, 70.
MCCUL[AGH, P. (1983). Quasi-likelihood functions. Ann.Statist., 11, pp. 59–67.
NELDER, J.A. and WEDDERBURN, R.W.M. (1972). Generalised linear models. J.R.Statist.Soc., A, 135, pp. 370–384.
PREGIBON, D. (1980). Goodness of link teats for generalised linear models. Appl. Statist., 29, pp. 15–24.
RICHARDS, F.S.G. (1961). A method of maximum likelihood estimation. J.R.Statist.Soc., A, 135,pp. 370–384.
SCALLAN, A.J. (1984). Fitting autoregressive processes in GLIM. GLIM Newsletter, No. 8.
SCALLAN, A.J., GILCHRIST, R. and GREEN, M. (1984). Fitting parametric link functions in generalised linear models. To appear in Computational Statistics and Data Analysis.
SENG, C.C. (1982). Covariance stabilizing transformations and a conjecture of Holland. Ann.Statist., 10, pp. 313–315.
THOMPSON, R. and BAKER, R.J. (1981). Composite link functions in generalised linear models. Appl.Statist., 30, pp. 125–131.
WEDDERBURN, R.W.M. (1974). Quasi-likelihood functions, generalised linear models and the Gauss-Newton method. Biometrika, 61, pp. 439–47.
WILKINSON, G.N. and ROGERS, C.A. (1973). Symbolic description of factorial models for analysis of variance. Appl.Statist., 22, pp. 392–399.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1984 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gilchrist, R., Scallan, A. (1984). Parametric Link Functions in Generalized Linear Models. In: Havránek, T., Šidák, Z., Novák, M. (eds) Compstat 1984. Physica, Heidelberg. https://doi.org/10.1007/978-3-642-51883-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-51883-6_28
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7051-0007-7
Online ISBN: 978-3-642-51883-6
eBook Packages: Springer Book Archive