Automated cleaning by score

Estimated reading: 2 minutes

The quickest and easiest method to clean a data file is to clean it automatically by score. To do this, proceed as follows:

Open cleaning dialogue

Select »Clean/Mark« from the menu at the top right of the application. The cleaning dialogue opens.

Define the threshold values below which data records are to be removed.
- The default settings can be used in most cases. However, if required, you can also specify other score thresholds according to which the cleaning should be performed.
To activate or change the cleaning parameters, click on the checkboxes.

Confirm the action by clicking on the button »Apply Cleaning«.
All data records with a score below the respective threshold values are removed.
In the »Cleaned data« view, the removed data records are then not included in the statistics and diagrams.
In the data table view, the removed data records are displayed as »excluded« to allow a manual verification.
In the tab »Mark« tab, you can specify the score from which respondents should be marked in the data table view with an asterisk. This has no influence on the cleaning process.

Another way of data cleaning is the option »Number of remaining data records«.
If you select this option, you can specify how many data records should be left after the cleaning process.
- This function is particularly useful if it is no longer possible to collect additional data. Otherwise, we recommend the cleaning by score threshold.

Confirm this process by clicking on the button »Apply Cleaning«.
- All respondents with the lowest scores are removed until the defined sample size limit is reached.

If you have any further questions about the automated cleansing of data, please contact us at support@redem.io