A. Variable costing is not used to estimate or forecast a dependent variable using historical data on an independent variable.

B. Linear programming is not used to estimate or forecast a dependent variable using historical data on an independent variable.

C. Flexible budgeting is not used to estimate or forecast a dependent variable using historical data on an independent variable.

D. Historical data on each of the independent variables being considered – packages shipped, miles shipped, and pounds shipped – should be regressed separately in a simple regression against the historical data on shipping costs, the dependent variable. From each separate regression, the resulting coefficient of correlation should be evaluated to determine whether there is a strong correlation between the independent variable and historical shipping costs. The coefficient of correlation is a numerical measure between +1 and -1 that results from the regression analysis and indicates the strength of the relationship between the independent and dependent variables. A coefficient of correlation that is close to +1 indicates a strong positive linear relationship between the independent and dependent variable, while a coefficient of correlation that is close to -1 indicates a strong inverse, or negative, linear relationship between the independent and dependent variable.