ABSTRACT
This chapter provides, where possible, techniques originally devised for regression models to the whole class of generalized linear models, and develop new ones for aspects of the general class that have no analogues in the restricted one. It presents a number of techniques, both formal and informal, for checking the internal consistency of models, looking for both systematic deviation and for isolated unusual points. Model-checking techniques may be either informal or formal. Informal techniques rely upon the human mind and eye to detect pattern. Such methods take a successful model to be one that, among other things, leaves a patternless set of residuals. The chapter looks at model-checking procedures associated with particular points in the data, especially those that appear in some way at variance with the pattern set by the remainder. It deals with the case of a single possibly discrepant point.
