This chapter has discussed multiple regression analysis. We began by considering the multiple regression model. We next discussed the least squares point estimates of the model parameters, the assumptions behind the model, and some ways to judge overall model utility-the standard error, the multiple coefficient of determination, the adjusted multiple coefficient of determination, and the overall F test. Then we considered testing the significance of a single independent variable in a multiple regression model, calculating a confidence interval for the mean value of the dependent variable, and calculating a prediction interval for an individual value of the dependent variable. We continued this chapter by discussing using squared terms to model quadratic relationships, using cross-product terms to model interaction, and using dummy variables to model qualitative independent variables. We then considered how to use the partial F test to evaluate a portion of a regression model. We next discussed multicollinearity, which can adversely affect the ability of the t statistics and associated p -values to assess the importance of the independent variables in a regression model. For this reason, we need to determine if the overall model gives a high R² , a small s , a high adjusted R² , short prediction intervals, and a small C. We considered how to compare regression models on the basis of these criteria, and we also showed how to use stepwise regression and backward elimination to help select a regression model. We concluded this chapter by showing (1) how to use residual analysis to check the regression assumptions for multiple regression models, (2) how to use various diagnostics to detect outlying and influential observations, and (3) how to use logistic regression to estimate the probability that an event will occur.