Binary Logistic Regression
Unlike linear regression, which is used to classify or predict values on a continuous variable (e.g., estimated premorbid intelligence), logistic regression attempts to classify or predict a discrete, categorical variable from among continuous and/or discrete predictors, such as whether or not a patient will be successful in cognitive rehabilitation (yes/no; the dichotomous criterion variable) based on premorbid intellectual functioning (the continuous predictor). Much like other sciences, clinical neuropsychology’s predilection for applying this model in research is tied to its inherent structure as a discipline, which involves the use of scientific nomenclature to describe cognition and behavior, and to compartmentalize syndromes into diagnostic entities.
- Wright, R. E. (1995). Logistic regression. In L. G. Grimm & P. R. Yarnold (Eds.), Reading and Understanding More Multivariate Statistics (pp. 217–244). Washington, DC: American Psychological AssociationGoogle Scholar