Review of methodology for addressing high-frequency repeat victimisation in Crime Survey for England and Wales estimates

Last updated:
6 July 2016

Opening date: 6 July 2016
Closing date: 13 September 2016
Category: Crime and Justice

Background

In order to be able to reliably estimate trends in incidents of crime from the Crime Survey for England and Wales (CSEW), in cases of repeat victimisation the survey (and its predecessor, the British Crime Survey) has always only included the first five incidents of a series within estimates. There has been criticism of this methodology for failing to adequately recognise the very real occurrence of repeat victimisation, and in 2015 we committed to reviewing the method for addressing high frequency repeat victimisation going forward.

We commissioned an independent review of the current and alternative methods for addressing high-frequency repeat victimisation. This review proposed a set of recommendations and we ran a public consultation asking users for their feedback on these recommendations between 6 July and 13 September 2016.

We asked

  • Should the current methodology of capping repeat incidents at 5 be changed?
  • Is capping at the crime-specific 98th or 99th percentile a suitable alternative?
  • What are your views on the use of annualised multiple year aggregations of data, and the use of different time periods for different crime types?
  • Is revising previous CSEW figures based on any new methodology a priority?

You said

  • The current methodology should be changed as it masks levels of repeat victimisation, especially for domestic violence and abuse
  • Capping at the 98th percentile would be a significant improvement, while still limiting the level of volatility added to the series; however some users favoured the complete removal of capping
  • The use of different time periods for different crime types when calculating annualised multiple-year aggregations would be unnecessarily confusing and complex
  • Revising previous figures is important for crime trend analysis

We did

We published a response on 7 November 2016 summarising the consultation feedback and the decisions that have been made based on this feedback. We will:

  • Change the current methodology of arbitrarily capping repeat incidents at 5
  • Adopt a lighter cap of the 98th percentile of victim incident counts for each crime type (calculated over a number of years)
  • Not use annualised multiple-year aggregations of data
  • Revise the time series back as far as possible
  • Make available uncapped estimates (with appropriate caveats) as part of our methodology information

We plan to implement the new methodology and revise the back series by July 2018 at the latest.

Contact details

Email: crimestatistics@ons.gov.uk

Related downloads