Data Quality Control Example Comparison of Crash Dataset 2013 with 2012

• September 12th, 2014

The purpose of this document is to present an example of the use of IMPACT as a data quality control tool. The crash data will be used as an example, and a past year (2012) will be compared with the most current year (2013) in order to determine discrepancies between the 2013 and the 2012 datasets. Typically there are not dramatic changes in the values/distributions of these data elements from one year to the next. If major discrepancies are found, this will be useful for at least one of the following purposes:

1. To determine any major changes that are occurring in the nature of crashes that need to
   be addressed from a traffic safety point of view.
2. To determine if there are critical items that seem to be neglected by those doing the data
   entry in the most recent year
3. To determine improvements that have been made in the data reporting

These will be considered in separate sections below, each in order of the extent of the differences
between the two years.