In double generalized linear models where we assume $y$ follows an exponential dispersion model, where the mean can be modelled as

$$g(\mu_i)=x_i^T\beta,$$ and the dispersion $(\phi)$ can be modelled as

$$h(\phi_i)=z_i^T\lambda$$ I have read in multiple articles that the deviance, which is used as response in the dispersion submodel can be assumed to be gamma distributed, so we can fit $\phi$ using a gamma GLM, but I do not understand why the unit deviance is gamma distributed.


1 Answer 1


The saddle-point approximation ensures that the unit deviance is approximately $\phi$ times a $\chi^2_1$ random variable, see Section 5.4.3 of my book with Peter Dunn (Dunn & Smyth, 2018). The scaled $\chi^2_1$ distribution is a special case of a gamma distribution.

In the simplest case of a normal linear model, the unit deviances are just the squared residuals $$d_i = (y_i-\mu_i)^2$$ In this case, standard normal linear assumptions imply that $$d_i \sim \phi \chi^2_1$$ where $\phi$ is the variance of $y_i$.

However, in Smyth (1989) I showed that the gamma approximation for the unit deviance is exact only for normal and inverse-Gaussian generalized linear models. I derived the exact distribution of the unit deviances for a gamma generalized linear model and showed that it is a new distribution that I have called "digamma".


Dunn PK, Smyth GK (2018). Generalized linear models with examples in R. Springer, New York, NY. DOI: 10.1007/978-1-4419-0118-7. ISBN: 978-1-4419-0118-7.

Smyth, G. K. (1989). Generalized linear models with varying dispersion. Journal of the Royal Statistical Society B 51(1), 47-60.

Smyth, G. K., and Verbyla, A. P. (1999). Adjusted likelihood methods for modelling dispersion in generalized linear models. Environmetrics 10, 695-709. http://www.statsci.org/smyth/pubs/Ties98-Preprint.pdf

Smyth, G. K., and Verbyla, A. P. (1999). Double generalized linear models: approximate REML and diagnostics. In Statistical Modelling: Proceedings of the 14th International Workshop on Statistical Modelling, Graz, Austria, July 19-23, 1999, H. Friedl, A. Berghold, G. Kauermann (eds.), Technical University, Graz, Austria, pages 66-80. http://www.statsci.org/smyth/pubs/iwsm99-Preprint.pdf


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.