Visual Profiling of Large Statistical Datasets a

Martijn Tennekes, Edwin De Jonge, Piet Daas
unpublished
National Statistical Institutes often have to deal with large datasets. Current quality assessments of these data are very limited. We present a visualization method, called tableplot, that aids in the quality assessment during data profiling and also is useful in data exploring. By using tableplots, analysts are able to discover strange data patterns, to examine the occurrence and selectivity of missing data and to observe the possible relationships between variables. We will discuss the use
more » ... l discuss the use of tableplots in data quality assessment, and show some of the results obtained when applying tableplots to Structural Business Statistics survey data.
fatcat:5ojmji4wbbhcfletse44c6xeei