Creating a data mining run

To create a data mining run, you start by selecting the type of run and the data configuration to use. After these selections, you specify a series of parameters that tell the application how to restrict or combine data, and which types of statistics to compute. You then submit the run and it is executed in batch mode. When the run is complete, you can view the results in tabular or graphical format.

If you have superuser permissions, you can create a run definition file to execute MGPS or logistic regression data mining runs from outside of the application. To do so, use the Create Definition File link. For more information about executing data mining runs externally, contact Oracle.

Note: If you have exceeded the disk space quota for your username, an error message appears when you attempt to create a run. To proceed, delete one or more of your existing runs or contact your system administrator to increase your quota.

1.         Click the Data Mining Runs tab.

The Data Mining Runs page appears.

2.         Click Create Run.

The Create Data Mining Run page appears.

3.         Select the type of run to create:

Note: Once you have selected a run type and continued to the next page, you cannot change the run type.

4.         If you selected Logistic regression (LR) data mining run, select the LR Type:

For more information, see Logistic regression computations.

5.         Select a data configuration.

The configuration references source data and determines which variables you can select for use in the run. Click Browse to select from a descriptive list of data configurations.

Note: For a logistic regression data mining run, Oracle recommends a data configuration that includes concomitant drugs, such as an AERS S+C configuration. For more information, see Logistic regression computations.

6.         To limit the run to cases that meet specified criteria only, check Define database restriction.

7.         Click Next.

The page that displays next depends on the selections you have made so far:

 

Related Topics