Linear models allow the description of a continuous, symmetric response in terms of a linear combination of predictor variables. Generalized linear models extend this framework to a wider range of response types, including categorical, binary, and skewed continuous responses. This allows a common approach to statistical inference in the fitting and testing of such models as well as diagnostic checking.
|Title of host publication||International Encyclopedia of Education|
|Editors||P Peterson, E Baker, B McGaw|
|Number of pages||6|
|Publication status||Published - 2010|
Faraway, J. J. (2010). Generalized linear models. In P. Peterson, E. Baker, & B. McGaw (Eds.), International Encyclopedia of Education (3rd ed., pp. 178-183). Elsevier. https://doi.org/10.1016/B978-0-08-044894-7.01331-2