Generalized Linear ModelsThe success of the first edition of Generalized Linear Models led to the updated Second Edition, which continues to provide a definitive unified, treatment of methods for the analysis of diverse types of data. Today, it remains popular for its clarity, richness of content and direct relevance to agricultural, biological, health, engineering, and ot |
Contents
Loglinear models | |
Binary data | |
An outline of generalized linear models | |
Models for continuous data with constant variance | |
5 | |
3 | |
Models with constant coefficient of variation | |
Conditional likelihoods | |
Models for survival data | |
Components of dispersion | |
Further topics | |
Model checking | |
Appendices | |
References | |
Quasilikelihood functions | |
Joint modelling of mean and dispersion | |
Models with additional nonlinear parameters | |
Other editions - View all
Common terms and phrases
algorithm aliasing analysis approximation assumed assumption asymptotic binary binomial distribution canonical link Chapter coefficient of variation computed conditional consider constant contrasts corresponding covariance matrix covariate classes cumulants defined degrees of freedom denote density depends derivative deviance discrepancy discussed dispersion parameter effects estimating equations estimating functions example exponential exponential family factor Fisher information Fisher information matrix fitted values gamma distribution given independent information matrix interaction inverse iteration levels likelihood function linear logistic model linear models linear predictor linear regression link function log likelihood log-linear model marginal maximum maximum-likelihood estimate mean method model formula multinomial non-linear Normal distribution Normal-theory observed obtained ΠΠΠover-dispersion parameter estimates plot Poisson Poisson distribution probabilities quadratic random variables regression models residual sum response sample scale Show standard errors statistic sufficient statistic sum of squares Suppose Table totals transformation usually variance function vector weights zero