Regression is a mathematical tool for quantifying the association between two or more variables. A fitted univariate linear regression model describes the average difference in one characteristic per unit difference in a second characteristic. Multiple regression is a widely used method for adjusting for several confounding characteristics simultaneously. The fitted multiple regression model can be used to predict the value of the outcome variable for any combination of predictor variables. The individual coefficients from a fitted multiple regression model represent the independent association between the predictor variable and the outcome variable, holding all other variables in the model constant.