Home»What»Data Core»Data Collection»Data quality»The fixes

Data Collection · Data quality · Component

The fixes

What was changed at source, rather than corrected downstream — because a cleaning step fixes one report and source fixes all of them.

The deliverable

What it is

Downstream cleaning is the common response because it is within the analyst’s control. It also has to be repeated in every report and diverges between them.

Source fixes are usually small: making a field required, replacing free text with a list, or removing a field nobody uses correctly.

One level in

What it is made of

Each element is a constituent part of the component. Follow one to see the attributes it carries.

  1. The change

    What was changed at the collection point.

    3 attributes: Change · Type · Implemented

    Learn

  2. The historical

    What happens to the data already collected wrongly.

    3 attributes: Treatment · Data before this is · Affected records

    Learn

  3. The verification

    Whether the fix worked.

    3 attributes: Quality before · Quality after · Verified

    Learn

Removing a field nobody enters correctly is underused and is frequently the right answer.

The other components in data quality

The measures

Completeness, accuracy, timeliness and consistency, per data set — measured rather than assumed.

Learn

The causes

Where quality problems originate, which is usually one step in collection rather than many small failures.

Learn
Back to data quality