Examining the Use of EWMA Charts for Monitoring the National Crime Victimization Survey

• Activity Number: 88
• Type: Contributed
• Date/Time: Sunday, July 29, 2012 : 4:00 PM to 5:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Elke Moons*+
• Companies: Statistics Netherlands
• Keywords: Moran's I statistic ; EWMA control chart ; national crime victimization survey (NCVS) ; spatio-temporal surveillance

Abstract

Monitoring feelings of (un)safety in relation to victimization of crime is one of the underlying reasons of why victimization surveys were initially developed. To this day, the variable measuring feelings of (un)safety remains one of the most important indicators to set out a policy concerning safety. Since 2008, the Dutch NCVS has a very complex design. It is a 2x2 mode survey that consists of: (a) a fixed part of about 20.000 respondents in order to ensure results at police-regional level and (b) a part with oversampling in areas that can change from year to year, depending on the community's needs. This complex and flexible design requests for a tool that monitors the main results from the survey and - when required - signals unusual outcomes. Visualizing the data helps, but in addition an EWMA control chart for global spatial statistics (Moran's I) is proposed here. In the event that a control chart signals, one can further examine the local spatial statistics to determine the source of the signal. This paper shows the results of these analyses and indicates how they can be used to characterize the effects of shifts in the spatial dispersion across the country.