Response Optimizer - View Model
main topic     see also 

Stat > Regression > Binary Logistic Regression > Response Optimizer > View Model

Displays information to help you determine whether you are using the correct model for optimization. This dialog box does not take any input.

Minitab automatically stores the most recent model for a response variable each time you run the analysis. Any model that you previously fit for that response variable is overwritten. For this reason, it is important to verify that the currently stored model is the correct model.

Response optimizer does not use the data in the worksheet. Instead, Minitab estimates the optimal variable values based on stored models. You must fit a model before you can use the response optimizer. If you want to optimize multiple responses, you must fit a model for each response separately. The optimal values are accurate only if all models represent the true relationships.

You can fit a model with different variables for each response. However, a variable in one model cannot be the response in another model. If a variable was not included in the model for a particular response, the optimization plot for that response-variable combination shows no change in the response when the variable changes.

Read the Stored Model Overview for more details.

Dialog box items

Model Type: This dialog displays only the binary logistic regression models in this worksheet that can optimize responses.

Response: Choose a response variable. The drop-down list displays all responses that have a model in the active worksheet.

Terms: Displays the terms that are in the last model that you fit for the specified response variable. Use your knowledge of the analysis' history to determine whether the current terms in the model correspond to the correct model. The terms list does not take any input.

Status: Displays the status of the model associated with the response variable. If the model is out-of-date, you need to re-fit the model before you can generate the optimal variable values. A model is out-of-date when the data have changed since you fit the model.