Complete the following steps to specify the columns of data that you want to analyze and how you want to fit the model.

- In Responses, enter the columns of numeric data that you want to explain or predict with the factors. If you enter more than one response, Minitab fits a separate model for each response. The response is also called the Y variable.
- Under Type of Model, choose the type of model that you want to fit.
- Mixture components only: The response is assumed to only depend on the proportions of the components in the mixture. For example, paint color only depends on the proportions of the pigments that are used in the mixture.
- Mixture components and process variables: The response is assumed to depend on the relative proportions of the components and the process variables, which are factors in an experiment that are not part of the mixture, but might affect the blending properties of the mixture. For example, the flavor of a cake depends on the cooking time and cooking temperature, as well as the proportions of the cake ingredients.
- Mixture amount experiment: The response is assumed to depend on the proportions of the components and the amount of the mixture. For example, the yield of a crop depends on the proportions of the insecticide ingredients and the amount of the insecticide applied.

- Under Analyze Components in, choose how you want to express the components in the model. You can choose either Proportions or Pseudocomponents. For more information, go to Amounts, proportions, and pseudo-components scales for representing the data in a mixtures design.
- Under Model Fitting Method, choose whether you want to fit the model with all of the terms that you specify in the Terms dialog or whether you want to use a stepwise procedure to identify a useful subset of the terms that you specify. For more information about stepwise procedures, go to Basics of stepwise regression.
- Mixture regression: Select to fit the model with all of the terms that you specify in the Terms dialog.
- Stepwise: This procedure removes and adds terms to the model for the purpose of identifying a useful subset of the terms that you specify in the Terms dialog.
- Forward selection: This procedure starts with an empty model, or includes the terms you specified to include in every model. Then, Minitab adds the most significant term for each step.
- Backward elimination: This procedure starts with all potential terms in the model and removes the least significant term for each step.

In this worksheet, Flavor is the response and contains the flavor scores. Emmenthaler, Gruyere, and Broth are the components. The values in these columns are the mixture proportions. In this design, the proportions in each row sum to 1. Temperature is a process variable.

C1 | C2 | C3 | C4 | C5 | C6 | C7 | C8 | C9 |
---|---|---|---|---|---|---|---|---|

StdOrder | RunOrder | PtType | Blocks | Emmenthaler | Gruyere | Broth | Temperature | Flavor |

1 | 16 | 1 | 1 | 0.6000 | 0.0000 | 0.40 | 80 | 55 |

2 | 1 | 1 | 1 | 0.4000 | 0.0000 | 0.60 | 80 | 32 |

3 | 10 | 1 | 1 | 0.3000 | 0.3000 | 0.40 | 80 | 85 |

4 | 15 | 1 | 1 | 0.2000 | 0.2000 | 0.60 | 80 | 52 |

5 | 13 | 0 | 1 | 0.3750 | 0.1250 | 0.50 | 80 | 57 |

6 | 11 | -1 | 1 | 0.4875 | 0.0625 | 0.45 | 80 | 56 |

7 | 2 | -1 | 1 | 0.3875 | 0.0625 | 0.55 | 80 | 45 |

8 | 9 | -1 | 1 | 0.3375 | 0.2125 | 0.45 | 80 | 71 |