O'Reilly logo

Foundations of Linear and Generalized Linear Models by Alan Agresti

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

CHAPTER 8 Quasi-Likelihood Methods

For a GLM ηi = gi) = ∑jβjxij, the likelihood equations

depend on the assumed probability distribution for yi only through μi and the variance function, vi) = var(yi). The choice of distribution for yi determines the relation vi) between the variance and the mean. Higher moments such as the skewness can affect properties of the model, such as how fast converges to normality, but they have no impact on the value of and its large-sample covariance matrix.

An alternative approach, quasi-likelihood estimation, specifies a link function and linear predictor gi) = ∑jβjxij like a generalized linear model (GLM), but it does not assume a particular probability distribution for yi. This approach estimates {βj} by solving equations that resemble the likelihood equations (8.1) for GLMs, but it assumes only a mean–variance relation for the distribution of yi. The estimates are the solution of Equation (8.1) with vi) replaced by whatever variance function seems appropriate in a particular situation, with a corresponding adjustment for standard errors. To illustrate, a standard modeling approach for counts assumes that {yi} are independent Poisson ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required