Summary
Highlights
Regression analysis is a method for modeling relationships between variables, allowing for the inference or prediction of one variable based on one or more others. The variable being predicted is called the 'dependent variable,' while the variables used for prediction are 'independent variables' (also known as predictor or input variables).
Regression analysis is used for two main goals: to measure the influence of variables on another variable (research-based, e.g., factors influencing children's concentration) or to predict a variable based on others (application-oriented, e.g., predicting hospital stay duration or product purchases in an online store).
There are three main types: simple linear regression, multiple linear regression, and logistic regression. Simple linear regression uses one independent variable, while multiple linear regression uses several to predict a dependent variable. Both simple and multiple linear regressions predict a 'metric' (numerical) dependent variable.
Logistic regression is used when the dependent variable is 'categorical' (e.g., yes/no, diseased/not diseased). The most common form is binary logistic regression, where the outcome has two possible values. Independent variables in all regression types can be nominal, ordinal, or metric. Categorical independent variables with more than two categories can be handled using dummy variables.
Examples include: simple linear regression (e.g., does weekly working time impact hourly wage?), multiple linear regression (e.g., do weekly working hours and age influence hourly wage?), and logistic regression (e.g., do weekly working hours and age influence the probability of burnout, where burnout is a 'yes' or 'no' category).