Various types of regression models exist, depending on the nature and distribution of the variables, the number and complexity of the predictors, and the purpose of the analysis. Linear regression assumes a continuous dependent variable with a linear relationship to independent variables. Logistic regression is used when the dependent variable is binary, such as 0 or 1, yes or no, or success or failure. Multiple regression includes more than one independent variable in the analysis. Polynomial regression captures nonlinear relationships between the dependent and independent variables by adding higher-order terms or powers of the independent variables. For instance, linear regression could be used to predict store revenue based on customer numbers and average purchase amount, logistic regression to predict whether a customer will buy a product or not based on age, gender, and previous purchases, multiple regression to predict customer satisfaction score based on service quality, delivery time, and product quality, and polynomial regression to predict fuel efficiency of a car based on speed and engine size.