ABSTRACT
This chapter has shown that when the outcome variable is categorical, logistic regression can be used to analyse a data set which contains one or more predictors. It has demonstrated the use of logistic regression when the outcome has two possible values. It has shown that there are a number of parallels with linear regression such as simple, multiple and sequential regression. However, there are also a number of differences including the use of odds ratios to measure the link between the outcome and a predictor variable.
