Select the option that best describes how you want to enter the data to predict the response and to create confidence intervals and prediction intervals.

Complete the following steps if you want to enter the variable settings directly in the dialog.

- To perform this analysis in Minitab, go to the menu that you used to fit the model, then choose Predict. For example, if you fit a Poisson model, choose .
- From Response, select a response variable to predict.
###### Note

Only response variables with up-to-date models from the same analysis are in the list. If you do not see a response that you want, re-fit the model. For more information, go to Stored model overview.

- (Optional) Select Include covariates in prediction to include covariate values in the predictions. If your model contains but you do not include them in the prediction, Minitab averages the prediction over the covariates. For more information, go to What is a covariate?. This option is available only for models that you fit using Fit General Linear Model or Analyze Factorial Design.
- From the second drop-down list, select Enter individual values.
- In the table, enter at least one value for each variable. You must enter the same number of values in each column. For categorical variables, select a value from the drop-down list. For continuous variables, you must enter numeric or date/time values.

Complete the following steps if you want to enter columns of data.

- To perform this analysis in Minitab, go to the menu that you used to fit the model, then choose Predict. For example, if you fit a Poisson model, choose .
- From Response, select a response variable to predict.
###### Note

Only response variables with up-to-date models from the same analysis are in the list. If you do not see a response that you want, re-fit the model. For more information, go to Stored model overview.

- (Optional) Select Include covariates in prediction to include covariate values in the predictions. If your model contains but you do not include them in the prediction, Minitab averages the prediction over the covariates. For more information, go to What is a covariate?. This option is available only for models that you fit using Fit General Linear Model or Analyze Factorial Design.
- From the second drop-down list, select Enter columns of values.
- In the table, enter one column for each variable. Each column must contain the values for one variable. You must enter the same number of values in each column. For categorical variables, the column must contain values that match the values that you used to fit the model. For continuous variables, the column must contain numeric or date/time data.Minitab stores the results in the worksheet columns and does not display them by default. To display the results, select the items in the Results sub-dialog box.

In this worksheet, columns C1–C4 represent the columns of data for the original analysis on which the model is based. Salary is the response. Gender_New, Years_New, and Quality_New contain the values for the predictors that are used to predict values of Salary.

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

Salary | Gender | Years | Quality | Gender_New | Years_New | Quality_New |

50 | M | 4 | 95 | M | 6 | 70 |

76 | F | 13 | 67 | M | 10 | 84 |

68 | F | 7 | 78 | F | 15 | 60 |

80 | M | 11 | 88 | F | 12 | 57 |