Difference between revisions of "Logistic regression"
Jump to navigation
Jump to search
| Line 1: | Line 1: | ||
'''Logistic regression''', abbreviated '''LR''', is a type of curve fitting. It used for categorical dependent (outcome) variables. Examples of categorical dependent variables are: (1) pass/fail, (2) dead/alive. | '''Logistic regression''', abbreviated '''LR''', is a type of curve fitting. It used for categorical dependent (outcome) variables. Examples of categorical dependent variables are: (1) pass/fail, (2) dead/alive. | ||
== | ==Types of logistic regression== | ||
===Multinomial LR=== | ===Multinomial LR=== | ||
If the dependent variable is categorical and the categories are mutually exclusive (e.g. ''benign'', ''suspicious'', ''malignant'', ''insufficient''), ''multinomial logistic regression'' is used. | If the dependent variable is categorical and the categories are mutually exclusive (e.g. ''benign'', ''suspicious'', ''malignant'', ''insufficient''), ''multinomial logistic regression'' is used. | ||