You can fit the following linear, quadratic, or cubic regression models:
||Y = β0+ β1x + e
||Y = β0+ β1x + β2x2+ e
||Y = β0+ β1x + β2x2+ β3x3+ e
Another way of modeling curvature is to generate additional models by using the log10 of x and/or y for linear, quadratic, and cubic models. In addition, taking the log10 of Y may be used to reduce right-skewness or nonconstant variance of residuals.
When Minitab fits the quadratic or cubic models, Minitab standardizes the predictors before it estimates the coefficients. The standardization reduces the multicollinearity among the predictors. The reduction ensures that the multicollinearity is so low that Minitab is unlikely to exclude any predictors from the model. The output shows the unstandardized coefficients in the original units of the predictors."