Verifying Data

You may want to verify the integrity of the data in your spreadsheet for logical consistency and completeness. Although some types of errors in the data may never be detected, there are many ways to perform data verification based on general criteria that the data are expected to meet.

STATISTICA provides a data verification feature to create verification conditions (this feature is available by selecting Verify from the Data tab or menu). After you specify the verification conditions and click OK, data in the spreadsheet (or the selected range) will be tested sequentially (one case at a time) for its consistency with the conditions you specify in the Verify Data dialog box.

When a case is found that does not meet the conditions, the respective row of data in the spreadsheet will be highlighted, and the Data Verification dialog box will be displayed. This dialog box is used to decide to ignore the inconsistency (and continue or stop the verification process), or edit (correct) the case. After you edit the case, you can continue the verification.

The data verification process can be illustrated in more detail by using an example. In a spreadsheet that includes the variables Gender, Age, and Pregnant, you may want to verify the accuracy of the data in several different ways. For instance, you may want to verify the accuracy of the data in the Age column by creating a verification condition that checks for values less than 0 or greater than 200. Or, you can create a verification condition that checks multiple variables; for example, a verification condition can check for cases that have Male as the value for the Gender variable and Yes as the value for the Pregnant variable.

See also, Verification Conditions Syntax Summary.