Fit Regression Model - Options
main topic     see also 

Stat > Regression > Regression > Fit Regression Model > Options

Use to:

·    Perform a weighted regression

·    Specify the confidence level and type of confidence interval

·    Choose the type of sum of squares

·    Perform a Box-Cox transformation on your response data when the residuals are not normally distributed or do not have constant variance

When you transform your data, Minitab transforms the response data and uses it in the analysis. Under most conditions, it is not necessary to correct for nonnormality unless the data are highly skewed. When you use Box-Cox, all response data must be greater than 0. Check your model carefully before using the Box-Cox transformation.

Dialog box items

Weights: Enter a numeric column of weights to perform weighted regression. Weights must be greater than or equal to zero. The length of the weights column must match the length of the response column.

Confidence level for all intervals: Enter the confidence level. The default is 95.

Type of confidence interval: Choose the type of confidence interval: two-sided (default), lower bound, or upper bound.

Sums of Squares for Tests: Choose a sums of squares for calculating F and p-values. Typically, use the adjusted SS. Use sequential SS  to determine the significance of terms by the order that they enter the model.

Adjusted (Type III): Measures the reduction in the SS for each term relative to a model that contains all of the remaining terms.  

Sequential (Type I):  Measures the reduction in the SS when a term is added to a model that contains only the terms before it.

Box-Cox Transformation

No transformation: Choose to use your original response data.

Optimal l (lambda): Choose to have Minitab search for an optimal value.  

l  = 0 (natural log): Choose to use the natural log of the data.

l  = 0.5 (square root): Choose to use the square root of the data.

l : Choose to transform the data using another l value. Enter a value between -5 and 5.