General Linear Model
The general linear model incorporates a number of different statistical models: ANOVA, ANCOVA, MANOVA, MANCOVA, ordinary linear regression, t-test and F-test. It is a versatile statistical method which incorporates one more continuous variables (such as intake scores) and categorical (or class variables) such as diagnosis, to predict a continuous dependent variable, such as the change score.
The difference between the predicted score and the actual score is referred to as the residual score, or in the case of change scores, the
residualized change (or gain) score. The residualized gain score reflects the extent the patient's change score differs from all other patients in the sample after matching for intake scores and any other
case mix adjustment variables collected at intake.
For more information on general linear model see:
General Linear Model: wikipeida
General Linear Model: Planetmath.org
--
JebBrown - 09 Jan 2007