While checking regression model assumptions, an engineer generates the following plot of residuals versus predicted Y. Which of the actions below is the most appropriate next step?
When evaluating residuals from a regression model, a Black Belt discovers that she has outliers in the data. What is best course of action for the outliers?
In analyzing some data, you first try multiple linear regression with all the factors and with interactions (example: Factor A times Factor B is interaction AB) You obtain a multiple regression equation of the form: Response = 15 + .13 A - .30 B - .02 C - .00001 AB + .0000004 AC - .00000013 BC +.000000 ABC. The p-values for most of the factors and interactions are between 0 and .05, except interactions BC and ABC, which have p-values between .4 and .9. Which of the following approaches might be appropriate to simplify the equation?