Competing with High Quality Data: Concepts, Tools, and Techniques for Building a Successful Approach to Data Quality

Chapter 7 Prioritization of Critical Data Elements (Funnel Approach)¹

7.0 Introduction

In Chapter 6, we discussed how to identify, validate, and assess critical data elements through subject-matter expertise, the rationalization matrix, profiling, DQ rules, and DQ scores. In this chapter, we discuss how to prioritize these CDEs and reduce the number of CDEs to be measured and monitored, using the funnel approach. We demonstrate the applicability of this approach with the help of a case study. The funnel approach presented in this chapter is useful in the Assess and Improve phases of DAIC.

7.1 The Funnel Methodology (Statistical Analysis for CDE Reduction)

With the input from business SMEs and the CDE rationalization matrix, we can derive a set of CDEs for a given business case. This aspect was discussed in Chapter 6. However, the size and complexity of a big company's data population make it economically infeasible to carry out 100 percent data quality checks for all CDEs for any ongoing operational process. Therefore, it is not only desirable but also necessary to reduce the number of CDEs being measured. To this end, sampling methodologies are employed. This allows for efforts to be concentrated on monitoring and improving the data quality of the CDEs that are of the greatest business or organizational importance.

In this section, we discuss how to reduce the number of CDEs using sampling-based statistical analysis as part of the funnel methodology. By applying statistical ...