Table 1

Comparison of linear, logistic and multiple regression

LinearLogisticMultiple
Purpose
Examines the relationship between one independent variables with one dependent continuous variableCalculates the likelihood of event with binary outcome (ie, yes or no)It is an extension of simple linear regression and examines the relationship between one or more independent and dependent variables simultaneously
Nature of dependent and independent variables
  1. Dependent variable should be continuous

  2. Independent variables could be at any level of measurement

  1. Dependent variable should be categorial

  2. Independent variables could be at any level of measurement

  1. Dependent variables should be continuous

  2. Independent variables could be at any level of measurement

Assumptions
  1. Assumes that the distribution of dependent data is normal or Gaussian

  2. Requires a linear relationship between dependent and independent variables

  1. Assumes that the distribution of dependent data is binomial.

  2. It does not require a linear relationship between dependent and independent variables

  3. The independent variables should not be correlated

  1. Assumes that the distribution of dependent data is normal or Gaussian

  2. Requires a linear relationship between dependent and independent variables

  3. The independent variables should not be correlated. Higher correlation among the independent variables may affect the relationship between independent and dependent variable

Nature of curve
It uses a straight lineIt uses an S-curveIt uses a straight line
Example
Examining the relationship between hours of training and levels of patient self-care and predict how long training should last for every unit increase in self-care levelsEstimating the likelihood of development of pressure ulcers (dichotomous outcome: yes or no) due to longer hospital stay, number of times of positioning, BMI (Body Mass Index) and ageExamining the relationship between hours of training and patient self-care levels while controlling for other variables (eg, family support, duration of disease) that may affect the relationship