Analysis of a Mixture Experiment - Model Tab

Select the Model tab of the Analysis of a Mixture Experiment dialog to access the options described here.

Model

Use the options in the Model group box to specify the terms to be included in the model. The common mixture models are shown below for the example case of a 3-component design (see Cornell, 1990b, for additional details).

Linear.

y = b1*x1 + b2*x2 + b3*x3

Quadratic.

y = b1*x1 + b2*x2 + b3*x3 + b12 *x1*x2 + b13 *x1*x3 + b23*x2*x3

Special cubic.

y = b1*x1 + b2*x2 + b3*x3 + b12 *x1*x2 + b13 *x1*x3 + b23*x2*x3 + b123*x1*x2*x3

Full cubic.

 y = b1*x1 + b2*x2 + b3*x3 + b12 *x1*x2 + b13 *x1*x3 + b23*x2*x3 + d12*x1*x2*(x1-x2) +   d13*x1*x3*(x1-x3) + d23*x2*x3*(x2-x3) + b123*x1*x2*x3

(Note that the dij's are also parameters of the model.)

Ignore some effects/Effects to ignore

The first time that you click the Ignore some effects check box or the Effects to ignore button, the following warning is displayed:

Note: after pooling effects, the results for fitting pseudo-components and the original components may no longer be the same.

Because of the recoding of factors involved in the computation of pseudo-components (see the Summary: Estimates, pseudo-components option on the Quick tab or the ANOVA/Effects tab), the confounding of factor effects is different when you analyze the recoded factor settings as compared to the original factor settings. As a consequence, when you pool effects into the error term, then the model based on the original factor values may no longer be equivalent to the model based on the recoded (pseudo-component) factors. You can always compare the mean-square-errors that are reported in the spreadsheet with the Summary: Estimates, pseudo-components option on the Quick tab or the ANOVA/Effects tab and the spreadsheet with the Estimates, original components option on the ANOVA/Effects tab.

Select the Ignore some effects check box or click the Effects to ignore button to display the Customized (Pooled) Error Term dialog box, which contains a list of all higher-order terms in the current model. Highlight the effects that you want to ignore, that is, that you want to pool into the error term.