Chapter 9: Models for Proportions: Binomial GLMs
Chapters 5– 8 develop the theory of glms in general. This chapter focuses on one specific glm: the binomial glm. The binomial glm is the most commonly used of all glms. It is used to model proportions, where the proportions are obtained as the number of ‘positive’ cases out of a total number of independent cases. We first compile important information about the binomial distribution (Sect. 9.2), then discuss the common link functions used for binomial glms (Sect. 9.3), and the threshold interpretation of the link function (Sect. 9.4). We then discuss model interpretation in terms of odds (Sect. 9.5), and how binomial glms can be used to estimate the median effective dose ed50 (Sect. 9.6).
- Dala, S.R., Fowlkes, E.B., Hoadley, B.: Risk analysis of the space shuttle: pre-Challenger prediction of failure. Journal of the American Statistical Association 84(408), 945–957 (1989)Google Scholar
- Dunn, P.K., Smyth, G.K.: Randomized quantile residuals. Journal of Computational and Graphical Statistics 5(3), 236–244 (1996)Google Scholar
- Hewlett, P.S., Plackett, T.J.: Statistical aspects of the independent joint action of poisons, particularly insecticides. II Examination of data for agreement with hypothesis. Annals of Applied Biology 37, 527–552 (1950)Google Scholar
- Lumley, T., Kronmal, R., Ma, S.: Relative risk regression in medical research: Models, contrasts, estimators, and algorithms. uw Biostatistics Working Paper Series 293, University of Washington (2006)Google Scholar
- Myers, R.H., Montgomery, D.C., Vining, G.G.: Generalized Linear Models with Applications in Engineering and the Sciences. Wiley Series in Probability and Statistics. Wiley, Chichester (2002)Google Scholar